Caterina Caccavella, Vittorio Fra, Andreas Ziegler +2cs.CV
Dense semantic segmentation allocates computational resources uniformly across the entire image, regardless of scene complexity or task relevance. Inspired by biological vision, we investigate whether semantic understanding can be achieved more efficiently through digital foveated perception. We introduce a lightweight active-vision pipeline that combines saliency-driven fixation selection, high-resolution foveal observations, low-resolution contextual information, semantic accumulation, and adaptive computation. Beyond conventional dense prediction metrics, we use object-level evaluation to measure semantic understanding under sparse observations. On ADE20K-Object, a single foveated observation achieves 95.9% of the baseline Top-1 accuracy and 96.9% of the baseline Top-3 accuracy while requiring only 4.7% of the computational cost. At the scene level, semantic accumulation recovers 90.6% of the baseline object recall while using 58.6% of the computation. These results suggest that substantial semantic understanding can emerge from sparse observations when computation is allocated selectively, highlighting active vision as an efficient alternative to uniform dense processing and motivating evaluation protocols beyond conventional pixel-wise segmentation metrics.
Denoising diffusion models are the dominant architecture for image generation, whereas most natural language generation and modeling are primarily handled by well-known transformer architectures employing attention mechanism. Here, we show that diffusion models also inherently use an attention mechanism very similar to that of transformers. Therefore, attention emerges as a universal machine learning principle, based on a general training objective. We also show similarities in basic functional principle of auto-encoders and attention-based models. These equivalences allows us to interchange these designs based on practical requirements. As an example, we can reformulate the diffusion framework to reduce the lengthy training process and computation-intensive image generation. Using this approach, a simplified algorithm is proposed for image generation which is based on attention mechanism. Results show that the attention-based implementation achieves comparable performance with significantly less effort and computational resources.
Visual aliasing, also known as the doppelganger problem, remains a key challenge for structure-from-motion (SfM): visually similar but physically distinct surfaces can produce incorrect image matches and degrade reconstruction quality. Previous work mitigates this issue with geometry-aware foundation-model features, but places a heavy transformer classifier on top of the backbone, making large-scale disambiguation expensive. We introduce XDG, an efficient visual disambiguation model designed for scalable SfM. Our key observation is that a 3D foundation model already performs the cross-view geometric reasoning necessary for visual disambiguation, so doppelganger classification should adapt the backbone representation directly rather than relearn pair reasoning in a separate heavy decoder. XDG fine-tunes Depth Anything 3 with lightweight LoRA adapters and repurposes its camera tokens as compact pair-level classification tokens. A compact MLP head predicts whether a candidate image pair observes the same 3D surface. Extensive experiments show that XDG provides a favorable accuracy-efficiency tradeoff: it remains competitive with the state-of-the-art disambiguation method across pairwise and reconstruction benchmarks and delivers more than a 3x inference speedup. On individual LaMAR scenes containing thousands of images, XDG saves more than 10 hours of visual disambiguation processing. Code is available at https://github.com/xtcpete/xdg.
Lukas Kuhn, Lucas Maes, Giuseppe Serra +4cs.CV cs.AI
Video carries the temporal structure of the physical world, yet learning representations from it has remained computationally expensive: prevailing self-supervised methods either prevent representation collapse through architectural asymmetries, coupling an exponential-moving-average target encoder, a stop-gradient, and a capacity-limited predictor, or circumvent it by reconstructing masked content in pixel space. We introduce LeVJEPA, the first video encoder trained under LeJEPA's collapse-free objective, which dispenses with both. A single encoder is trained with an invariance loss over global and local views of a clip, regularized by SIGReg, which excludes collapse with a provable guarantee. The architecture reduces to an encoder and a projector, and the objective to a single hyperparameter. This formulation admits two properties. First, the cost of pretraining is governed by the number of tokens the encoder observes; uniform random token dropping renders this number small while simultaneously improving downstream accuracy. At matched epochs on identical data, LeVJEPA matches or surpasses V-JEPA 2 across ViT-S/B/L at 5.6 to 20.8x less pretraining compute, and at matched total FLOPs it exceeds the strongest video baseline by 7.6 points on ImageNet-1K while remaining competitive on motion-centric benchmarks. Second, since no asymmetry between branches is required, the encoder can be trained with block-causal attention at no measurable accuracy cost: temporal ordering becomes a property of the encoder itself. Against a compute-matched DINOv2 trained on frames of the same videos, LeVJEPA approaches the image-pretrained encoder on appearance-centric evaluation while nearly doubling its motion-centric accuracy. These results indicate that, once its computational overhead is removed, video becomes a viable and in several respects preferable substrate for general-purpose visual pretraining.
Vision-based wheat phenotyping requires repeated measurements under deployment constraints, from growth-stage recognition to wheat-head counting and organ segmentation. Plain Vision Transformers (ViTs) provide a common architecture for these tasks, but quadratic attention limits high-throughput and edge inference. Training-free token merging is attractive because it can be inserted into trained models without retraining. We provide a systematic benchmark of ToMe and Mutual Pair Merging across growth-stage classification, wheat-head detection, and wheat-organ segmentation, measuring task quality, throughput, token count, and peak GPU memory, with additional Raspberry Pi 5 measurements. The benchmark reveals a clear hierarchy: classification is highly merge-tolerant, while detection and segmentation are constrained by repeated instances, thin organs, dense boundaries, reconstruction, and runtime overhead. Optimized attention backends can erase apparent speedups, so deployment value must be profiled on the target runtime rather than inferred from token count.
We introduce RS$^3$-Prune, a training-free token-pruning recipe that instantiates as a small set of inference time hooks atop existing video object segmentation (VOS) networks. Modern VOS models have converged on a common, expensive design: an image encoder produces a dense token grid for every frame, and a memory bank accumulates these tokens across all previously processed frames to condition future predictions. As a video grows longer, the resulting token budget governs both per-frame latency and peak GPU memory. Hence these models break on use cases such as --- long-form video or real-time deployment on memory-bounded accelerators. In this work we argue that the right axis along which to compress memory-bank VOS is the token budget itself. RS$^3$-Prune operates in two precise locations within an arbitrary memory-bank VOS pipeline: at the boundary between the image encoder and the memory-attention readout, where we restrict the queries that participate in the cross-frame attention to only a small, geometrically informed subset; and at the boundary between the memory encoder and the memory bank, where we restrict which tokens are ever permitted to enter the bank to those that lie within the object's spatial extent. Over various established benchmarks, RS$^3$-Prune delivers up to $38.8\%$ FPS speedup and reduces $13.1\%$ peak memory usage, while preserving a competitive $\mathcal{J}$&$\mathcal{F}$ compared to the unmodified VOS networks.
Huaiyuan Qin, Gabriel James Goenawan, Zihang Lin +2cs.CV cs.LG
While linear attention is a compelling mechanism for high-resolution object detection due to its reduced cost for global token mixing, converting the Softmax-attention ViT backbone of a trained detector into a linear-attention one is not a trivial drop-in replacement. Directly swapping the attention operator leads to severe performance degradation, and generic label-free distillation, though effective for classification, often fails on detection tasks. We argue that the central challenge is \textit{detector-interface preservation}: the converted backbone must reproduce the exact feature tensors expected by the fixed downstream detector, rather than merely imitating internal Softmax hidden states. To address this, we introduce Detector-Interface Distillation (DiD), a label-free conversion method that exclusively trains the linear-attention backbone by aligning detector-facing interface tensors with those of a frozen Softmax teacher. On DOTA-v1.5, DiD substantially outperforms established baselines and matches supervised, fully trained linear models. Adaptation completes in roughly 87 minutes on 4 GPUs, and the linearized backbone cuts inference latency by ~62% and peak memory by ~49%. We hope our findings offer the community a simple, label-free route to reusing trained Softmax detectors as efficient linear ones, and encourage interface-aware objectives in future architecture-conversion work.
François Costa, Raphael Kreft, Eckhard Goedeke +6cs.CV
Multi-view computer vision pipelines typically rely on accurate sparse keypoints and robust descriptors. While incorporating line features has shown clear benefits for matching and pose estimation, existing point-line approaches remain inefficient: they detect points and lines separately, use increasingly heavy networks, and depend on CPU-bound heuristics that hinder real-time performance. We introduce a Unified Efficient Points and Lines (UPAL) feature extractor that jointly extracts keypoints, line segments, and feature descriptors within a single lightweight architecture. A shared backbone provides common representations that feed different branches for point and line features. Line segments are recovered through an accelerated post-processing stage, an enhanced and highly efficient variant of the LSD algorithm. UPAL matches or exceeds state-ofthe-art performance in both point and line applications while significantly reducing computational cost, achieving, for instance, a 4x speedup and 10x smaller memory footprint over the ALIKED + DeepLSD pipeline. Code is publicly available at https://github.com/francois141/upal.
Harold Haodong Chen, Zhiyu Hou, Wen-Jie Shu +4cs.CV
The rapid evolution of text-to-image (T2I) generation models has effectively solved the foundational challenge of raw pixel synthesis, shifting the community's focus toward fulfilling increasingly intricate user requests. While recent agentic image generation workflows enhance static inference with advanced capabilities like external knowledge retrieval and iterative reasoning, they mostly operate in isolated silos with fixed ``one-size-fits-all" topologies. This inevitably leads to severe compute-mismatch, where simple queries are forced through computationally heavy pipelines. To bridge this gap, we present GenRouter, the first unified workflow routing framework for agentic image generation. We first formulate GenCanvas, standardizing diverse agentic pipelines into a universal set of foundational primitives and executable templates. Operating over this unified space, GenRouter adaptively routes heterogeneous prompts to their optimal workflows via (i) demand profiling, (ii) experience matching, and (iii) Pareto filtering. Extensive experiments across diverse benchmarks demonstrate that GenRouter achieves superior visual alignment while reducing execution costs by over 95% and latency by 65% compared to heavyweight static pipelines. Furthermore, the system continuously self-evolves via accumulated experience, enabling robust zero-shot generalization that boosts performance and halves computational overhead.
Video Diffusion Transformers (DiTs) spend most of their compute inside the Self-Attention operation, whose cost grows quadratically, $\mathcal{O}(n^2)$, with the number of latent tokens $n$. For the task of video generation, the token count is large, so this term dominates runtime and memory, and thereby caps the resolution and duration we can generate. Linear $\mathcal{O}(n)$ and low-rank $\mathcal{O}(nk)$ surrogates of Self-Attention trade the full softmax $QK^T$ for cheaper kernels, but rarely recover the original's expressivity, leaving a stubborn quality gap. Motivated by this, we propose SQuad, a Sub-Quadratic Attention Distillation framework that achieves a complexity of $\mathcal{O}(n\sqrt{n})$ in the resulting distilled Attention, naturally balancing the efficiency v/s expressivity trade-off. Instead of training our own Video DiT from scratch, which is prohibitively expensive, we fit a pretrained full softmax Self-Attention DiT into our proposed SQuad-Attention one by distilling the former in two stages: Flow-Matching Supervised Fine-Tuning (SFT), followed by improved Distribution Matching Distillation (DMD2) which additionally makes the sampling more efficient. On the Wan~2.2 5B text-to-video model, SQuAD matches the quadratic teacher on VBench ($83.20$ v/s $83.08$) while cutting the per-step per-block attention FLOPs by $\sim$$67\times$ and attention latency by $\sim$$11\times$, and end-to-end DiT latency by 2$\times$, all while also generating a video in only $6$ Neural Functional Evaluations (NFEs) instead of the default $100$.
Foundation segmentation models excel at generating high-quality, class-agnostic masks, but they struggle to associate these proposals with specific target objects. This semantic gap severely hinders their deployment in downstream applications like robotic manipulation, which demand precise unseen objects segmentation. Existing approaches attempt to resolve this by relying on exhaustive 3D object model priors, inherently introducing prohibitive computational overhead and complex, multi-stage pipelines. To address these limitations, we propose SOS (Streamlined Object-conditional Transformer for model-free Segmentation). SOS completely eliminates the reliance on 3D models, requiring only a single reference image per target object. Central to our framework is a novel Object-Conditional Transformer that learns identity-anchored queries, unifying mask generation and target identification into a single feed-forward pass. This streamlined design drastically improves both structural and computational efficiency. Extensive evaluations across multiple benchmarks demonstrate that SOS establishes a new state-of-the-art for model-free unseen objects segmentation, delivering accurate and high-efficiency performance. The project page and code are available at https://sos-seg.github.io/.
Do feed-forward networks (FFNs) in visual grounding decoders add essential computation once a pretrained vision-language model has already encoded image and language context? We compare a four-block attention-only decoder (A4), a matched four-block attention-plus-FFN decoder (S4), and an eight-block attention-only parameter control (A8) over frozen VLM features. A4 matches or slightly exceeds S4 on RefCOCOg and Ref-Adv-s. FineCops-Ref reveals a small A4 deficit of 0.52 percentage points at IoU@0.5 (95% CI [0.12, 0.95] in favor of S4), but A8 recovers it and finishes 0.26 points above S4. Official FineCops levels do not show a monotonic increase in the gap. A4 reduces trainable decoder parameters by 44.4% and cached-decoder latency by 10.1%, although end-to-end latency remains backbone-dominated. These results concern the trainable grounding decoder, not a complete attention-only VLM.
RGBA videos combine RGB appearance with an alpha channel, enabling animated assets to be applied across arbitrary backgrounds, which are heavily used in gaming industry. However, generating high-quality RGBA animations for games remains challenging for two reasons. First, most existing RGBA video datasets are dominated by photorealistic content, with limited coverage of game assets. Second, the traditional generate-then-matte pipelines estimate alpha only after RGB synthesis, so semi-transparent regions are often blurred by background, resulting in unstable matting outputs. More recently, many methods have begun to model RGB and alpha jointly, but existing approaches are mostly text-conditioned, and still have unresolved issues in efficiency and quality. To address these challenges, we introduce GameAlpha-2.4K, a 2.4K-clip game-style RGBA video dataset built with matte-friendly synthesis, multi-hypothesis alpha recovery, and compositing-based quality gates. Using this dataset, we train a reference-conditioned RGBA video generator that jointly produces RGB frames and alpha mattes in a single pass. To improve efficiency, we propose a visibility router that identifies transparent tokens in an early stage and bypasses their later DiT updates, while x_0-lock guides them along the original flow-matching schedule toward self-predicted endpoints. Our model obtains lower FVD than traditional two-stage pipelines, and the visibility router skips 35% of token evaluations in the final two DiT denoising steps, providing a 1.2x backbone speedup with negligible quality degradation compared to dense inference.
Yan Zeng, Changlu Guo, Oskar Kristoffersen +3cs.CV
Visual counterfactual explanations aim to change classifier decisions through realistic and localized edits while preserving decision-irrelevant content. Existing DDPM-based methods typically perform classifier-guided editing along a long reverse denoising trajectory. The changing noise levels make semantic editability and spatial control difficult to balance, and the editable state is noisy, whereas the target classifier is trained on clean images. As a result, these methods require either costly recursive denoising or low-quality one-step estimates to obtain classifier-facing clean images. We propose FiRe, a Fixed-noise Refinement framework for visual counterfactual explanations. Rather than following a reverse denoising trajectory, FiRe maps the input to a fixed noise level and iteratively refines the noisy state at that level. To provide clean images for classifier guidance, FiRe first adapts Pixel Mean Flow to visual counterfactual explanation, enabling direct clean-image prediction from noisy states. To make fixed-noise refinement produce minimal and localized counterfactual edits, FiRe introduces three FiRe-specific controls: a dynamic dual-mask strategy, adaptive guidance, and early stopping, which determine where edits accumulate, which changes become visible, and when refinement stops. Experiments on five tasks across three datasets show that, compared with the strongest recent baseline, FiRe achieves about 3$\times$ faster online inference and 8$\times$ fewer FLOPs while obtaining comparable or state-of-the-art counterfactual quality.
Grzegorz Gruszczynski, Pawel Olszowiec, Michal Byra +2cs.LG cs.CV
Vision Transformers (ViTs) achieve strong image-recognition performance, but their parameter count grows linearly with depth when each block is independently parameterized. Single-block recurrent ViTs (bViT) remove this growth by repeatedly applying one shared block. Rather than proposing a new architecture, we fix a bViT and provide a controlled empirical characterization of three training and inference regimes under a common CIFAR-100 protocol, asking: (i)~when does recurrence beat independently parameterized depth---at matched FLOPs or at matched parameter memory? (ii)~when a residual recurrent block is trained through an ODE solver, does solver order act as numerical refinement or as an architectural bias? and (iii)~what does robustness beyond the training horizon cost in nominal accuracy? We find that standard ViTs remain preferable when FLOPs are the primary constraint, whereas recurrent ViTs offer a better accuracy--parameter trade-off under memory constraints. Consistent with the standard view of residual networks as Euler discretizations of ODEs, the continuous-time analogue of a residual recurrent block is the state-subtracted vector field $\dot{z}=F_θ(z)-z$; although known in principle, this distinction is easy to violate when the block is wrapped as a black-box vector field, and we qualify the cost at few accuracy points. Because the vector field is learned jointly with the solver, higher-order solvers act as a solver-induced architectural bias rather than a numerical-accuracy improvement, and their gains are not uniform. Finally, stage-wise deep supervision traces an accuracy--robustness frontier: it does not improve nominal accuracy, but degrades gracefully far beyond the training horizon, where naive recurrence collapses to near-random performance.
Structured pruning enhances the efficiency of deep neural networks (DNNs) by eliminating groups of parameters during inference. Previous methods mostly reduce computational complexity (FLOPs), while semantic segmentation performance (mIoU) slightly drops. Accordingly, recent dynamic structured pruning methods aim at reducing the performance drop, while lowering the FLOPs even more. However, on the ADE20K and Cityscapes benchmarks, our study reveals that on a GPU platform such dynamic methods exhibit a surprisingly low frame rate far below a simple static approach, while having comparable results in mIoU and FLOPs. To address this issue, we propose a static structured pruning method for attention layers, that achieves both, a lower FLOPs and a high frame rate [fps] of the SegFormer network, the latter increased by up to 34% relative on the Cityscapes dataset, while having no mIoU performance drop at all. Our so-called StaticSegFormer method is strongest for small encoders and large images.
Zero-shot visual anomaly detection has achieved remarkable progress, with recent vision-only approaches further improving performance while simplifying the inference pipeline. However, existing methods typically perform dense computation over all images and spatial tokens, despite the fact that normal samples dominate real-world scenarios and anomalies usually occupy only small regions. Token pruning offers a promising solution, but introduces an asymmetric pruning risk in anomaly detection: retaining normal tokens mainly incurs redundant computation, whereas removing anomalous tokens may eliminate the only evidence for detection and localization. This risk is particularly severe in early layers, where pruning provides the greatest computational benefit but anomaly semantics remain unreliable. We propose KeepAD, a defect-preserving token pruning framework that formulates token selection as high-recall, anomaly-aware routing. In shallow layers, KeepAD combines coverage-preserving selection over local $2\times2$ patch neighborhoods with deterministic anomaly rescue to reduce the risk of discarding subtle defects. In deeper layers, frozen normal and abnormal prototypes guide pruning under an image-adaptive token budget, aggressively removing low-risk normal tokens while preserving local anomaly evidence. Dense-to-sparse self-distillation further supervises early token routing without introducing additional inference overhead. Experiments on six industrial and seven medical zero-shot anomaly detection benchmarks show that KeepAD reduces the token retention ratio to below $20\%$, while limiting the average degradation in image-level and pixel-level AUROC to within $2.7$ percentage points. At the most aggressive operating point, KeepAD achieves a $7.9\times$ speedup over the strongest CLIP-based baseline.
Video dataset distillation aims to compress a large video dataset into a compact surrogate set that preserves its training utility. Most existing approaches synthesize condensed videos through iterative optimization, whose cost is amplified by the temporal dimension. Rather than further reducing the number of optimized variables, we investigate whether effective distilled videos can be constructed without gradient-based optimization of the stored videos. Such a construction-based approach must address three challenges: selecting informative temporal segments, covering diverse intra-class variations under a limited videos-per-class budget, and increasing the information carried by each stored sample. To this end, we propose ProtoBlend, an efficient select-allocate-blend framework. First, teacher-guided temporal clip selection retains a high-confidence segment from each source video. Second, cluster-guided prototype allocation partitions the selected clips in the teacher feature space and assigns one distilled slot to each intra-class cluster. Third, each prototype is blended with an in-cluster anchor, while their teacher predictions are combined using the same coefficient to provide mixture-source supervision. Experiments on four trimmed action-recognition benchmarks demonstrate that ProtoBlend achieves a competitive accuracy-efficiency trade-off without iterative optimization of the distilled videos.
Audio-driven video generation (A2V) has achieved promising progress in synthesizing temporally coherent and audio-visually aligned videos, yet its inference remains expensive due to the iterative denoising process of diffusion models. Existing caching methods mainly exploit temporal redundancy in visual features while overlooking the cross-modal alignment of A2V, where audio drives visual generation with highly non-uniform temporal importance. In this paper, we identify two levels of misalignment in existing A2V caching methods: temporal-semantic and computation-storage misalignment. To address them, we propose EchoCache, an energy-guided cross-modal caching framework for efficient A2V generation. EchoCache leverages audio time-frequency energy as a saliency anchor to guide latent-level cache updates and further introduces a dynamic timestep-latent caching mechanism with quantized cache management for joint efficiency and memory optimization. Extensive experiments on mainstream A2V models show that EchoCache consistently improves the latency-quality trade-off while preserving generation quality and audio-visual consistency. In particular, on Wan2.2-S2V over the EMTD benchmark, EchoCache achieves a 2.46x speedup with the best overall performance. Code is available at https://github.com/IF-LAB-PKU/EchoCache.
Recent advances in large vision-language models (LVLMs) have enabled long-video understanding and analysis. However, processing the large number of frames in a video incurs substantial computational overhead. Existing methods reduce LVLM inference costs by scoring frame-query relevance before inference and selecting keyframes accordingly. Nevertheless, the distribution of relevant frames varies across queries, and these methods often need to score hundreds or thousands of frames. To address this limitation, we propose CSES, a training-free semantic keyframe selector that adaptively determines the numbers of frames to score and keyframes to select. CSES estimates the prominence of the frame-query relevance profile to guide active acquisition and adapt the temporal coverage of each input. It then formulates keyframe selection as a coverage problem that jointly accounts for semantic relevance, temporal redundancy, and visual redundancy. Active acquisition and keyframe selection terminate based on coverage saturation. The selection objective is monotone and submodular, enabling greedy optimization with a standard approximation guarantee. Experiments with four LVLMs on two benchmarks show that our method preserves accuracy while scoring $4$-$13\times$ fewer frames and selecting $18.4\%$-$20.5\%$ fewer input keyframes than existing baselines. CSES further achieves a $3.1$-$5.4\times$ speedup in frame selection over baselines.
Kamil Książek, Piotr Suszyński, Michał Jan Włodarczyk +2cs.CV cs.AI
Vision foundation models, such as DINOv2, learn highly expressive representations but rely on massive, opaque architectures that demand substantial computational power and memory. To provide an interpretable-guided and efficient solution to this issue, we first propose a spectral analysis and new visualization technique for individual attention heads based on the Laplacian eigenvectors of their attention maps. Building upon recent observations regarding the block structure of Vision Transformers, we perform semantic clustering of attention heads and identify functional redundancies. Leveraging these insights, we introduce SAPER (Soft Attention PrunER), an end-to-end differentiable pruning framework based on the LapSum Soft Top-K approach. Extensive experiments on ImageNet-1K demonstrate that SAPER achieves a highly favorable accuracy-efficiency trade-off, outperforming the competitive RAPTOR baseline in FLOPs reduction while preserving strong classification performance.
Ultra-high-definition (UHD) image restoration must balance the aggregation of spatially recurring degradation cues with the preservation of localized image structures. Compact aggregation can reduce redundant processing but may attenuate edges, textures, and other fine structures. Existing approaches manage UHD restoration cost through downsampling, window partitioning, or cluster-based token reduction; yet many of them do not explicitly retain information that is poorly represented by shared aggregation. In this study, we propose a Context-Detail Decoupled State Space Model (CoDe-SSM) for UHD restoration, which processes aggregated context and clustering residuals in separate pathways. The context modeling pathway, implemented by the Global Cluster Scan Module (GCSM), aggregates features into $K$ input-dependent cluster centers and applies selective SSM reasoning over the resulting fixed-order sequence, enabling cross-region context sharing while decoupling computational cost from spatial resolution. The detail recovery pathway, implemented by the Local High-Frequency Module (LHFM), processes the clustering residual with an input-derived high-frequency mask and a sparse mixture of convolutional experts. Extensive experiments on five UHD benchmarks and five degradation types demonstrate that our explicit context-detail decoupling strategy yields substantial gains in restoration quality while maintaining desirable efficiency.
Simon Roy, Mark Bong, Giovanni Beltramecs.CV cs.IR
Operational Earth observation increasingly calls for answering queries such as ``find the image pairs where a new building appeared.'' This means searching an archive of before-and-after (bi-temporal) satellite image pairs and ranking each pair by how well it matches a natural-language description of the change. The component that performs this match, the fusion module that combines the ``before'' and ``after'' views, must be run at query time across many candidate pairs, so its speed largely sets the cost of every search. We present a controlled comparison of how to build that module. Using one fixed image encoder (a frozen CLIP model) and one training recipe for all variants, we evaluate eight designs drawn from three families: attention, state-space models (Mamba), and learned compression (our Temporal Bottleneck Fusion, TBF). Each design is tested on two benchmarks (LEVIR-CC and Dubai-CC) with ten random seeds, so the reported differences are statistically grounded. We outline three findings: first, a training-free two-stage search (a cheap difference model that shortlists candidates, followed by attention fusion that re-ranks them) matches or exceeds full-fusion recall on LEVIR-CC while cutting query cost $10$-$15\times$, with comparable R@1/R@5 on Dubai-CC; second, the linear-time scan of Mamba, attractive on paper, gives no speed benefit at the patch counts typical of vision transformers ($L{=}196$): the scan is limited by memory bandwidth, whereas attention maps cleanly onto parallel hardware; and third, compressing the fused representation (TBF) reduces parameters by $2.3\times$ and latency by $1.6\times$ for a change-only BLEU-1 cost of $0.007$, although more aggressive compression quietly discards change-relevant detail that aggregate metrics fail to reveal.
With the growth of gaming, animation, and virtual reality industries, the demand for efficient generation of stylized 3D assets is rapidly increasing. However, existing approaches still struggle to jointly preserve style fidelity, geometric consistency, and generation efficiency, as most of them still rely on indirect 2D-to-3D stylization pipelines. This motivates a native 3D stylization framework that can explicitly disentangle style from geometry while remaining efficient. To this end, we propose DreamStyle3D, an efficient framework for stylized 3D asset generation built on a Decoupled Dual Cross-Attention mechanism. Our method explicitly separates geometric and stylistic features to enable efficient style injection while preserving structural consistency, and further adopts a lightweight training strategy to enhance style consistency and model generalization. In addition, we build an automated data pipeline and construct a dataset of about 15K content-style-stylized triplets for training and evaluation. Extensive experiments demonstrate that our DreamStyle3D can generate high-fidelity, geometrically consistent stylized 3D assets within 10 seconds, substantially improving efficiency while maintaining superior style quality and offering a new solution for 3D content creation. The code and data are available at https://github.com/HVision-NKU/DreamStyle3D.
Modern computer vision pipelines remain fragmented, with tasks such as text-to-image generation, editing, restoration, and classical perception handled by separate models. We study Unified Visual Generation (UVG), where a single model produces diverse image-valued outputs through a unified multimodal interface. While diffusion-based systems dominate UVG due to strong quality and controllability, their iterative sampling incurs substantial inference latency, limiting practical deployment. To address these limitations, we propose UniGen-AR, a framework that pairs a general-purpose multi-modal language model (MLLM) with an efficient next-scale visual auto-regressive (VAR) decoder. This design retains the flexibility of MLLM-based conditioning while leveraging the sampling efficiency and latent unification properties of VAR models. In our framework, the MLLM encodes free-form instructions and control signals into a unified sequence, which guides the VAR decoder to generate image-valued outputs for over 15 tasks spanning four families. Empirically, UniGen-AR achieves up to $19 \times$ lower inference latency than diffusion-based baselines while maintaining or improving output quality. Our ablations further reveal that VQ-VAE tokenizer design, particularly codebook size and hierarchy, is a critical factor for VAR scalability in UVG. These results establish visual auto-regressive modeling as a compelling and efficient backbone for unified visual generation. Our project page is at https://zpbao.github.io/projects/unigenar.
Shreshth Saini, Neil Birkbeck, Yilin Wang +2cs.AI cs.CV cs.MM
Test-time search lets small video diffusion models rival larger ones, but costs 2-10x more. All candidates are fully denoised, although most are discarded. Training-free caching makes each rollout 2-3x faster at near-lossless quality. Composition is safe only if lossy caching preserves verifier rankings. We present the first study of whether caching corrupts candidate ranking in video test-time search. On Wan2.1-T2V-1.3B with an adaptive caching wrapper (~2x per-candidate speedup), ImageReward scores seed-matched cached and full rollouts. Median per-prompt Spearman rank correlation is 0.905, with 72% top-1 agreement on the VBench suite. VBench-2.0 replicates this result on a harder suite. Recomputing the cached winner at full compute retains 90-94% of the full-search gain. Errors cluster among near-tied candidates, making corruption self-limiting. This finding leads to CachedSearch. It explores every candidate with aggressive caching, then re-generates only the winner at full compute. At N=8, it captures 94.7% of best-of-N's gain at 63% of the cost. Capture rises with width. At matched budget, it searches twice as wide for 38% more gain. The result holds from 1.3B-14B across six models and four families: Wan, LTX, CogVideoX, and Hunyuan. Wan2.1-14B matches the 1.3B model's fidelity. Mid-trajectory pruning multiplies the exploration saving to 3.11x at 88.6% capture. Ports to other model families require recalibrating a single parameter, showing that fidelity tracks architecture rather than parameter count. CachedSearch is training-free, verifier-agnostic, and orthogonal to the search algorithm, making it a plug-in multiplier for test-time scaling.
Atiq Ur Rehman, Joseph Michael Donovancs.CV cs.LG stat.AP
High-resolution satellite imagery is the backbone of good land-cover classification, and without that, environmental monitoring, urban planning, and sustainable resource management all fall short. Deep learning architectures perform well in semantic segmentation, but the efficiency-accuracy trade-off across classical convolutional encoders is not well quantified under controlled, reproducible conditions. This study compares five architectures VGG16, MobileNetV2, InceptionV3, AlexNet, and CNN on the DeepGlobe Land Cover Classification dataset using three progressively optimized iterations to isolate regularisation, transfer learning, and architectural depth. To ensure performance differentials reflect architectural properties, all experiments used identical preprocessing, hyperparameter, and training protocols without data augmentation or class-imbalance correction. At 24.98 MB, MobileNetV2_v1 had the highest overall accuracy (0.7906) and mean Intersection over Union (0.4625), outperforming deeper alternatives like InceptionV3_v2 (125.17 MB, accuracy 0.7610) and VGG16_v2 (71.13 MB, accuracy 0.7653). Class-wise analysis showed strength in urban, agricultural, and water categories, but rangeland-barren confusion showed that architectural optimization alone cannot optimize spectrally similar minority classes. Strong spatial generalization and crisp boundary delineation were confirmed on held-out test imagery, validating operational applicability. These results show that lightweight, transfer-learned models can match or outperform deeper models in resource-constrained remote-sensing environments, enabling scalable land-cover mapping.
Sicheng Gao, Zhuyun Zhou, Yixuan Liu +3cs.CV cs.AI
Video super-resolution (VSR) using large-scale Diffusion Transformer (DiT) priors achieves exceptional perceptual quality but is often impractical due to the quadratic computational cost of processing dense spatio-temporal token sequences. Existing efficiency-oriented methods risk irreversible detail loss and temporal flickering, a vulnerability especially pronounced in one-step diffusion models. To address this, we propose TRaM-VSR, a Token Routing and Merging framework for adaptive token allocation, leveraging both context-aware video priors and network-level priors. First, token importance is estimated by fusing motion-sensitive temporal cues with semantic text similarity, isolating dynamic objects and structural boundaries. Next, this importance is further calibrated and adjusted by an offline planner to guide routing across optimally grouped network blocks. Technically, within each routed group, structurally critical tokens are processed in a high-fidelity local stream, while less informative tokens are aggregated into a compact global stream, both modulated by network depth and aligned with the multigranular nature of diffusion models. Extensive experiments show that TRaM-VSR accelerates inference significantly while preserving state-of-the-art reconstruction quality and robust temporal consistency. The code is available at https://github.com/Ree1s/TRaM-VSR.
End-to-end OCR systems based on vision-language models have achieved strong performance in complex document OCR, but their efficiency is limited by the large number of visual tokens produced from document images. Many of these tokens correspond to blank margins or visually redundant regions, yet directly applying generic visual token compression methods may remove OCR-critical fine-grained details. In this paper, we propose LayoutLite, a lightweight plug-and-play module for efficient document OCR. Instead of relying on explicit document layout detection, LayoutLite performs implicit layout analysis at the token level between the vision encoder and the language decoder. It aggregates multi-layer visual representations from the vision encoder, and predicts an importance score for each visual token with a lightweight scoring network. Low-information tokens are then removed before entering the language decoder while preserving the original spatial positional information of retained tokens. To train LayoutLite without human annotations, we cast token selection as a reinforcement learning problem and optimize it with a group-relative policy optimization objective driven by OCR output consistency, together with an auxiliary layout supervision signal to stabilize training. Experiments on OmniDocBench demonstrate that LayoutLite can substantially reduce visual token length and inference cost with negligible degradation in recognition quality. We further evaluate LayoutLite on two OCR-specialized VLMs, FireRed-OCR and Logics-Parsing-V2. Under up to 50% token compression, LayoutLite preserves almost the same score on both models while reducing prefill latency, FLOPs, and KV cache memory by over 40%, with only a small additional inference overhead. These results show that token-level implicit layout analysis is an effective and practical approach for accelerating VLM-based OCR systems.
Streaming video diffusion models have made substantial progress toward interactive and dynamic world simulation, but the nested autoregressive and denoising loops of conventional next-frame generation hinder real-time deployment. Recent rolling-window methods pipeline denoising across multiple consecutive frames at different noise levels, improving throughput and long-horizon stability. However, they tokenize every state at the same fine spatial granularity, leaving substantial noise-dependent redundancy in the joint denoising window. We propose Ms.Forcing, an efficient streaming video generation paradigm that adapts spatial granularity to each state's noise level. Its Multi-Scale Patchification (MSP) assigns coarser patches to noisier states, reducing the active-window token count by 45%, while Multi-Scale Self-Attention (MSSA) matches the density of visible non-sink keys and values to each query scale to further reduce attention cost. Because both schedules are fixed by window position, Ms.Forcing retains a static, hardware-friendly computation graph. We further introduce Homogeneous-Noise-Level DMD (H-DMD), which assembles each fake video from clean predictions sharing the same source noise level, thereby reducing the mismatch between DMD training sequences and inference-time rollouts. The multi-scale design helps offset the additional training cost of backpropagating through overlapping windows. We include both quantitative and qualitative experiments to show that Ms.Forcing reaches 22.84 FPS on a single H200 GPU, 39.6% faster than Rolling Forcing, while significantly improving VBench scores in both short video and long video generation setting.