While data-driven 3D shape correspondence estimation has recently seen substantial progress, robust matching under partial observations and strong non-isometric deformations remains challenging. Existing learning-based approaches often rely on hand-crafted descriptors or template-based representations, whereas recent generative models over functional maps suffer from high inference cost, limited interpretability, and poor generalisation to partial shapes. In response to these limitations, this paper introduces TokenMatch, a new transformer-based unified model for estimating 3D shape correspondences. Our feed-forward approach trained exclusively on BeCoS, a challenging non-isometric partial-to-partial shape-matching dataset, can generalise to matching full shapes without retraining or fine-tuning. TokenMatch uses self- and cross-attention mechanisms to efficiently learn patch-level and point-level relations as well as dense correspondences between shape pairs. Our core insight is that meshes can be adaptively tokenised into patches using shape curvature guidance, enabling effective learning of shape-specific geometric descriptors for correspondence estimation. We evaluate TokenMatch on standard benchmarks for partial and full shape matching, including CP2P, PSMAL, BeCoS, FAUST, SCAPE, and SHREC'19. Our method achieves consistently high performance, in most cases outperforming existing methods for partial and full shape matching in the mean geodesic error and intersection-over-union metrics, while also running faster at sub-second inference speeds.
Shravan Venkatraman, Wenshuai Zhao, Mohammad Hassan Vali +1cs.CV
We introduce S$^3$T (Self-Supervised Self-Distillation over Time), which, to the best of our knowledge, is the first fully self-contained framework for continuous video state tracking. Our method treats temporal sampling density as privileged information, based on the hypothesis that a denser view of the same clip recovers the running state more accurately. This view serves as the teacher, while a sparse-view student with the same weights learns to match its next-token distribution. The model generates its own target, so training requires no labels, separate teacher, or reward signal, and adds no inference cost. On LLaVA-OneVision-2-8B, S$^3$T improves VSTAT accuracy by $+1.74$ as a single model, $+2.38$ with souping, and $+2.70$ with additional vision-encoder adaptation, while prior self-evolving methods leave state tracking largely unchanged. The capability learned from unlabeled synthetic clips transfers to real videos, improving performance by $+7.95$ on VSTAT-YouTube state-tracking questions and $+4.50$ on MVBench Action Count.
Online 3D reconstruction models perform poorly on long videos. This happens because regressing poses relative to a fixed first-frame anchor forces extrapolation far beyond the training distribution. Small drifts accumulate and amplify into significant geometric collapse. However, we observe that per-frame depth remains stable throughout this failure. The backbone's local geometry remains intact; only the global pose head breaks down. Motivated by this decoupling, we introduce Scal3R. This approach reformulates online reconstruction as multi-reference relative pose querying. We use lightweight learnable tokens, which make up about ~1% of the parameters, and inject them into a completely frozen backbone via asymmetric attention. This setup queries poses relative to multiple past keyframes. An online pose-graph optimization system with loop closure suppresses long-range drift. Scal3R reaches convergence in 8 hours on a single GPU. It reduces the average ATE by over 60% on KITTI compared to the online baseline. It also achieves state-of-the-art performance across Virtual KITTI, Sintel, TUM-Dynamic, ScanNet, and 7-Scenes. Project page: https://linjohnss.github.io/scal3r/
Evaluating physical reasoning in video models is difficult because absolute motion measurements depend on frame rate, object scale, and camera calibration, all of which are often ambiguous or unavailable in generated video. We propose a different approach. When two objects in the same scene obey the same physical law, their motions must satisfy predictable relationships, and these relationships hold independent of calibration. We introduce Principia, a benchmark that evaluates Newtonian physics through relational consistency between paired objects. Principia spans eight phenomena - gravity, restitution, friction, rotational inertia, projectile motion, momentum, pendulum, and mass-spring oscillation - across translational, rotational, collisional, and oscillatory dynamics, using real-world scenes recorded under controlled protocols. We also introduce a calibration-independent consistency score that quantifies physical violation directly in image space. Across thousands of generations from six state-of-the-art video generators, no model exceeds 0.42 on Principia despite all scoring around 0.8 on VBench. Vision-language models are evaluated on their ability to detect relational physics violations, with the best model achieving only 67% accuracy and most performing near chance level.
Video editing spans diverse editing paradigms, yet achieving high-quality instruction-guided and subject-guided editing within a single unified framework remains challenging. We introduce EditVid, a training-free framework combining sparse causal memory for local coherence, correspondence-based post-attention token injection for long-range identity preservation, and soft latent blending for edit locality. The same framework supports instruction-guided and reference-guided edits, including style transfer, attribute modification, object insertion, part-level editing, and subject replacement. On FiVE, EditVid achieves 78.16 FiVE-Acc, compared with 58.95 for the strongest evaluated training-free baseline, while obtaining competitive results on IVEBench. A user study further shows a 51.8\% overall preference for EditVid over 7 competing methods.
Ye-Chan Kim, Seunghee Choi, SeungJu Cha +4cs.CV cs.AI
Weakly-Supervised Dense Video Captioning aims to localize and describe multiple events in untrimmed videos given only an ordered set of event-level captions per video. Recent work synthesizes auxiliary transition captions via LLM to provide additional vision-language alignment, but these captions lack visual grounding and are rigidly assigned to every inter-event gap at a fixed location and duration. To address these, we propose Seeing Before Synthesizing (SBS), a framework that adaptively provides visually grounded linguistic guidance only where warranted. Leveraging a VLM, we generate frame-level narratives for the inter-event gaps and detect transitions from the semantic variation across them. For identified transitions, we then refine inter-event temporal masks by blending the temporal midpoint with the semantic change point and selecting the width that maximizes vision-language alignment. Experiments on ActivityNet Captions and YouCook2 demonstrate state-of-the-art performance in both captioning and localization.
3D Foundation Models (3DFMs) such as VGGT have recently pushed the boundaries of 3D vision by predicting rich unified representations with feed-foward transformers. The scene representations learned by these models enable strong performance on multiple 3D vision tasks. In this paper, we investigate using their internal representations to infer 3D in the scene from new views. Our hypothesis is that in order to solve the task of 3D reconstruction, these models need to learn a representation that includes a large amount of general knowledge about 3D scenes. After showing that it is possible to decode hidden surfaces from internal 3DFM representations, we propose a method, Z3D, that estimates pointmaps in unseen views by doing latent diffusion on 3DFM representation. We show that Z3D can predict realistic depth maps for new views across multiple datasets.
Generative image models can now produce high-quality images, follow complex instructions, and support precise edits, but they still struggle to preserve who or what is being depicted. When generating or editing images of a specific subject, identity may drift as the pose, expression, appearance, viewpoint, or surrounding scene changes. Existing subject-driven methods make fundamentally different choices about where identity is represented: through the input context (GPT-Image-2, NB2), as trainable subject-specific model parameters (LoRA), or as a persistent identity layer (PHOTA IDENTITY) reusable across generations and edits. We systematically benchmark these paradigms across subject-driven generation, editing, restoration, and multi-subject settings, with tasks designed to increasingly stress identity preservation. Our results show that identity preservation remains a distinct limitation of current generative foundation models: strong image quality and instruction following do not necessarily imply strong identity fidelity, and identity degradation becomes more pronounced under iterative edits, small subject scales, severe image degradation, and multi-subject composition. Persistent identity substantially reduces this degradation across generation, editing, and restoration, consistently improving identity preservation when applied to different foundation models while maintaining comparable instruction adherence and perceptual image quality. These results suggest that identity does not simply emerge from increasingly capable generative models, but can instead be represented as persistent subject knowledge that is composed independently with the underlying generative model.
Video virtual try-on (VVT) aims to generate realistic videos of a person wearing a target garment. Recent methods leverage a keyframe-driven video generation paradigm to improve in-the-wild performance, yet they still rely on masks to localize try-on regions, making them vulnerable to large motions and severe occlusions. Although mask-free image-based try-on methods have shown promising results by leveraging large-scale pseudo data, extending this paradigm to videos remains difficult, as constructing video-level pseudo data is prohibitively expensive. Furthermore, coarse keyframe sampling and the scarcity of multi-view try-on data limit existing keyframe-driven methods in maintaining garment consistency and handling diverse try-on tasks. To address these challenges, we propose BooM-VVT, a mask-free VVT framework built upon the keyframe-driven paradigm. To achieve mask-free VVT, we introduce a multi-stage training strategy that leverages image-level pseudo data for mask-free localization learning, substantially reducing the need for costly video-level pseudo data. To improve garment consistency, we propose Garment-Sensitive Keyframe Sampling, which selects keyframes based on garment-relevant body regions to better capture garment appearance. We further introduce Frame-Shared 3D-RoPE to establish spatiotemporal correspondences between keyframes and target video frames for accurate garment-detail transfer. Finally, we construct OmniView, a large-scale multi-view try-on dataset to support reliable try-on video generation under complex camera viewpoints and diverse try-on tasks. Extensive experiments demonstrate that BooM-VVT achieves superior temporal consistency and garment fidelity over existing methods. Project page: https://boomvvt.github.io/boomvvt.
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.
Video diffusion models (VDMs) have achieved impressive progress in text-to-video generation, but their high memory and computational costs hinder practical deployment. Quantization-aware training (QAT) is an effective solution for compressing and accelerating advanced generative models without runtime overhead at inference. However, existing QAT methods suffer from a distinctive challenge in VDMs: while they often preserve prompt semantics, global layout, and coarse motion, the quantized model severely degrades visual details, texture fidelity, and sharpness. In this paper, we trace this degradation to the timestep-agnostic design of conventional quantization pipelines, which overlooks the stage-wise functionality of video denoising. In VDMs, early denoising steps mainly establish global structure and motion, whereas middle and late steps refine local appearance and high-frequency details. Based on this insight, we propose DSAQuant, a Denoising-Stage-Aligned Quantization-aware training framework for VDMs. During training, Denoising-Stage Oriented Supervision preserves teacher distillation in early steps for stable structure planning, while shifting later steps toward target-driven optimization to enhance detail reconstruction. During inference, Denoising-Stage Gated Guidance disables CFG in the final denoising steps to prevent it from amplifying quantization-induced errors into high-frequency artifacts. Extensive experiments on the Wan and CogVideoX families under W4A4 and W3A3 settings show that DSAQuant consistently outperforms the SOTA QAT baseline, improving the VBench average score by up to 6.60 under aggressive W3A3 quantization while preserving strong text-video alignment. These results demonstrate that effective VDM quantization requires not only reducing quantization error, but also aligning quantization training and inference with the stage-wise nature of video diffusion.
Bundle Adjustment (BA) is a cornerstone of 3D computer vision and has benefited from decades of advances in sparse optimization and numerical methods. It was originally developed for jointly optimizing camera intrinsics, poses and sparse 3D points. While extensions incorporate lines and other primitives, integrating richer geometric structures such as parallelism, coplanarity, or wireframes often introduces significantly increased computational cost and reduced numerical stability. In this paper, we propose a unified framework that extends bundle adjustment to jointly optimize geometric features and higher-order relations. We first introduce a taxonomy that distinguishes scalable geometric features with direct 2D measurements (e.g., points and lines), from groups encoding higher-order relations (e.g., coplanarity, parallelism, etc.), where we show that groups can be modeled as camera-like entities within the bundle adjustment framework. Building on this formulation, we propose that both group constraints and cross-feature relations (i.e., point-line associations) can be expressed through 2D reprojection measurements. By formulating group-induced and cross-feature reprojection errors, we preserve the sparsity structure of classical point-based BA under Schur elimination, while avoiding direct 3D regularization that degrades the conditioning and stability. Experiments on both real-world and synthetic datasets demonstrate runtime performance comparable to classical point-only bundle adjustment, while producing significantly richer 3D structures and improved geometric accuracy.
Verifying that manufactured batches of milling tools or carbide rotary burrs conform to production order sheets remains a largely manual and error-prone quality assurance task. Automating this process with computer vision faces a critical cold-start constraint since no labelled imagery is available, leaving manufacturer catalogue photography as the sole source of supervision. We investigate how far catalogue supervision can support an industrial recognition pipeline under domain shift, explicitly measuring the gap between catalogue separability and performance on held-out field photographs. Our findings reveal three key insights. First, off-the-shelf frozen feature extractors do not reliably separate the two task attributes, head shape and tooth profile, motivating targeted representation learning. Second, metric learning produces near-perfect unsupervised cluster discovery on catalogue images (adjusted Rand index 0.94--0.97), but less than half of this gain transfers to field photographs. Third, the largest transfer gains do not come from model scale or representation complexity, but from simple changes that reduce domain sensitivity: converting images to grayscale (+0.22) and constraining retrieval using the known order sheet via Hungarian assignment (+0.11). We therefore treat catalogue photography as a useful cold start rather than a deployment-ready training domain, and provide empirical baselines and an evaluation protocol for catalogue-to-field transfer in precision tool manufacturing.
Camera-conditioned world models generate interactive videos in which commanded actions should induce the expected scene changes while appearance, geometry, and temporal dynamics remain coherent. Existing rewards assess these requirements separately: geometry-based rewards estimate trajectory execution but cannot judge the visual quality of the executed motion, whereas image-based rewards measure frame quality without capturing action execution or temporal dynamics. We posit that a vision-language model (VLM) offers a shared reasoning space for relating actions to their visual outcomes. However, judging a complete long video against its full action sequence creates a lengthy, noisy context in which short-lived local action evidence can be missed or diluted. We present WorldReward, a VLM-based pairwise preference reward model that unifies action-consistency and visual-quality evaluation for camera-conditioned world models. WorldReward decomposes paired videos into action-aligned chunks, organizes each chunk into structured visual evidence, and aggregates chunk-level decisions by voting into separate video-level action and visual-quality preferences. To train it, we construct a large-scale reasoning-augmented preference dataset using structured judgments generated by a frontier VLM and refined through tool-based agent auditing and targeted human review. We further introduce WorldReward-Bench, a human-annotated benchmark measuring reward-model agreement with human preferences across action consistency, appearance quality, and motion quality. WorldReward achieves the highest agreement on all three dimensions, exceeding GPT-5.5 by 3.42, 1.45, and 3.56 percentage points, respectively. When used for RL post-training of HY-WorldPlay 1.5, it consistently improves both action execution and visual quality across short- to long-term horizons.
Thomas Lucas, Maxime Pietrantoni, Philippe Weinzaepfel +4cs.CV cs.LG
Generating complete 3D scenes from sparse, unconstrained views is a fundamental challenge in 3D vision which requires reasoning beyond observed content while remaining computationally tractable. Existing feed-forward reconstruction methods are inherently limited to content visible in the input images, while 3D generative modeling is hindered by the high computational cost of dense volumetric representations and the scarcity of large-scale 3D supervision. We introduce SPAR3S, a sparse voxel-aligned 3D latent generative model for conditional scene completion without requiring ground-truth 3D data for supervision. Our key insight is to formulate 3D scene generation in a structured, compact, voxel-aligned 3D latent space where only occupied voxels are represented. We learn this sparse latent space directly from multi-view images using photometric supervision via differentiable 3D Gaussian Splatting. Given a partial set of observed voxels encoded from sparse input views, scene completion reduces to predicting the missing latent tokens and their spatial support within the voxel grid. To this end, we train a masked autoregressive transformer that jointly models voxel occupancy and latent token values, enabling efficient and spatially consistent generation of unseen regions. We demonstrate the effectiveness of our method on synthetic indoor scenes, achieving higher novel-view quality than prior work. We further validate its generalization on RealEstate10k, highlighting its applicability to real-world data.
We present OctWorld, a video diffusion framework with persistent 3D memory for generating explorable, world-consistent, and high-fidelity visual scenes. Given a single image, OctWorld performs stable autoregressive world generation along user-specified camera trajectories. We focus on long-range generation, characterized by extended camera paths and wide viewpoint coverage, where preserving spatial consistency is particularly challenging when previously generated regions are revisited. To address this problem, we introduce OctMap, an extensible and spatially adaptive 3D memory that progressively fuses generated visual observations and their corresponding depth maps into a global representation. OctMap employs TSDF fusion within a dynamic sparse octree whose spatial resolution adapts to image evidence. This design preserves geometric and appearance details across diverse scene scales while maintaining low memory overhead. Experiments demonstrate that OctWorld generates long-range, spatially consistent videos and outperforms prior methods on both existing benchmarks and challenging long-range generation settings. OctMap also provides clear advantages over point-based caches and fixed-resolution TSDF volumes. Project page: https://maxtirerror.github.io/octworldpage/
Few-shot fine-grained image classification (FSFGIC) aims to classify similar images with limited labeled examples. This work highlights the critical yet underutilized role of phase information in capturing structural relationships within an image. This study introduces a novel plug-and-play amplitude-phase integration (API) module that effectively combines local and global frequency amplitude and phase information for obtaining more comprehensive feature descriptors. Additionally, a dedicated network, named PSF-Net, is proposed that adaptively fuses phase-based spatial and frequency information for FSFGIS. The designed PSF-Net can be easily integrated into standard episodic training architectures for end-to-end training from scratch. Extensive experiments on five public datasets demonstrate that the method outperforms existing state-of-the-art benchmarks.
Ernesto Lozano, Alberto Jaenal, Javier Civeracs.CV
3D foundation models (3DFMs) excel at predicting camera poses and dense depth from multiple views of a scene, showcasing strong zero-shot generalization. However, as metric scale is not observable from monocular images, their absolute scale predictions are typically inaccurate. Inertial measurement units (IMUs), present in most devices, naturally complement monocular cameras by observing scaled motion. We introduce VI3, a model-agnostic framework that metrically anchors a pretrained 3DFM using only IMU readings. VI3 initializes and preintegrates the IMU to obtain a metric motion reference, which is then used to recover the scale of the 3DFM outputs. Our method includes adaptable anchoring strategies tailored to diverse 3DFM architectures. Experiments on synthetic and real aerial datasets demonstrate that VI3 recovers metric scale without ground-truth supervision while preserving geometric consistency, acting as a fine refinement under well-conditioned motion and as a strong prior when motion is less informative.
Real-world image super-resolution (SR) increasingly relies on Diffusion Transformer (DiT) backbones, whose internal activations can be dominated by a small number of massive channels. Yet improving perceptual quality in these models still typically requires fine-tuning the network or attaching additional adapters, leaving this structured activation space largely unexplored for adaptation. We investigate whether dominant channels can instead serve as a compact adaptation interface for frozen DiT-based SR models. We first characterize their behavior in pretrained SR backbones and show through controlled interventions that they strongly affect reconstruction quality. Building on this observation, we introduce SPARK, a lightweight input-conditioned controller that predicts bounded per-channel affine transformations for only the selected channels, while keeping the SR backbone and VAE frozen. Dominant channels are identified through an online activation-ranking procedure, and only a small predictor conditioned on the low-resolution VAE latent is optimized. Experiments on three DiT-based SR backbones across DIV2K, RealSR, and DRealSR show consistent gains in both fidelity and perceptual quality while modulating only eight channels per stream and block. Controlled comparisons further show that these gains cannot be explained by parameter budget or access to the selected channels alone.
Marco Cipriano, Leonardo Zini, Alexandra Schild +5cs.AI cs.CV
Scalable Vector Graphics (SVG) generation is attracting increasing attention as generative models improve in expressiveness and controllability. Progress, however, is held back by the lack of domain-specific evaluation protocols: current practice relies on metrics designed for natural images, most notably CLIPScore, which was never trained on vector graphics and aligns only partially with human judgment. We introduce \textbf{\ours}, a human-aligned evaluation framework for text-to-SVG generation. Through controlled caption and image perturbations, we first show that CLIP-based scores barely react to the errors SVG generators actually make, such as wrong colors, counts, and spatial relations, and that off-the-shelf Vision-Language Model (VLM) judges, while more sensitive, respond unevenly across error types and SVG styles. We then introduce a human-annotated dataset for \textit{Semantic Alignment}, measuring how faithfully a generated SVG reflects its caption. Building on it, we develop two complementary evaluators: CLIP scorers adapted to vector graphics and then aligned to human preferences, for fast large-scale evaluation, and a VLM judge trained with supervised fine-tuning and reward-shaped reinforcement learning, for more expressive and interpretable assessment. Using both, we benchmark major open-source, commercial, and optimization-based SVG generators on an independent caption set.
Communities are fundamental spatial units that shape urban form and social life. Whether a residential compound is spatially open or enclosed affects mobility, access to public services, and equity, yet studies of Chinese fengbi xiaoqu remain largely qualitative or small-scale, limiting reproducible city-scale analysis. We address this gap by introducing GBA-GCs, a metropolitan-scale multimodal benchmark for locally grounded gated/open community recognition in China's Greater Bay Area, covering 37,444 residential compounds with aligned boundary polygons, high-resolution satellite imagery, Chinese metadata, and structured attributes, together with expert-verified labels, inter-annotator reliability, and official evaluation splits. Built on this benchmark, we present Multimodal Classifier for Gated Community (MCGC), a vision-centric multimodal framework based on DINOv3-SAT that fuses imagery, text, and structured cues via modality-aware cross-attention and adaptive gating to mitigate modality imbalance. MCGC consistently outperforms strong unimodal and multimodal baselines. Finally, we apply the validated model to metropolitan-scale mapping and report equity-oriented findings including spatial clustering of GCs, privatized green space, and reduced pedestrian connectivity. The benchmark, code, and release documentation are available at https://github.com/MinweiZhao/GBA-GCs.
Chuyan Chen, Haoxing Chen, Kun Chen +27cs.CV cs.AI
We introduce LLaDA-Image, a unified framework that pairs a 6B Diffusion Transformer (DiT) trained from scratch with a frozen vision-language understanding module built on the LLaDA2.0-Mini diffusion language model backbone. Instead of relying heavily on paired image-text data from the beginning, we first build a strong visual generative prior through image-only pre-training and mid-training. The generation pipeline comprises 220M samples, 98 of which are real images. For efficient and scalable optimization, we use parameter-free RMSNorm throughout the DiT together with the Muon optimizer. The resulting unified model produces highly photorealistic images while accurately following fine-grained editing instructions. We further distill LLaDA-Image into LLaDA-Image-Turbo, enabling fast inference in 2-4 sampling steps. On Qwen-Image-Bench, LLaDA-Image achieves overall scores of 53.53 and 53.38 on the English and Chinese tracks, respectively, setting a new state-of-the-art among open-source models on both tracks. To support further research on capable and efficient generative models, we release our model weights, training code, and detailed recipes.
JoyIndustrial VisCAD Team, Linxin Cai, Qiuhe Hong +10cs.CV cs.CL
Parametric computer-aided design (CAD) modeling is difficult to evaluate with a single metric. Existing CAD benchmarks often emphasize synthetic or CAD-native settings, limited input modalities, or executability and IoUs alone. We introduce RealCADBench, a benchmark for intent-to-program CAD modeling from real industrial design intents. It contains 12,632 tasks from 19 factory-automation categories and spans text descriptions, 2D engineering drawings, real product pictures, and rendered images for both Part and Assembly modeling. We report results on a 1,770-task evaluation slice: 1,745 Part tasks across four input regimes and RCB-Assm25, a 25-task assembly study used in every reported assembly comparison. Each method generates FreeCAD API Python, which a shared runtime executes to export the 3D model. We evaluate the exported model using executability, Solid IoU, Surface IoU, and a rubric-based visual-semantic identity Judge. Among the nine standalone frontier large models evaluated, no model leads all four metrics. Across six frontier-scale large models, executability ranges from 0.565 to 0.812, Solid IoU from 0.2841 to 0.5379, and Surface IoU from 0.112 to 0.217 across the four Part regimes. The highest regime-balanced composite comes from a different model than the leaders on the four component metrics. On RCB-Assm25, Codex with GPT-5.5 improves executability and both IoU metrics over standalone GPT-5.5, but lowers the Judge score by 6.98 percentage points, leaving GPT-5.5 as the Judge leader. We also observe recurring failure modes, most notably missing fine structures, loss of part identity, and incorrect assembly placement. These results show that execution alone is insufficient to characterize realistic CAD modeling and that frontier models and agents differ substantially across executability, IoUs, and visual-semantic identity.
Javier del Pino, Salvador Rodríguez, Alejandro Garabito +2cs.CV cs.AI
We present ENEAS, a unified, text-promptable method for instance tracking and semantic discovery. Text-promptable segmentation models, including the latest foundation models such as SAM 3, still suffer from temporal hallucinations, spatial fragmentation, and semantic misclassification: they fail to report target absence when an object leaves the field of view, segment local textures instead of the complete object during extreme close-ups, and prioritize visual features over ontological reality, so that visually similar artifacts such as statues, paintings, or reflections are segmented as target entities. ENEAS works two ways from a single method: precise tracking and high-quality segmentation of a unique instance, and open-concept discovery of every instance a text query names, resolved by a semantic verification layer. For tracking, we extend the geometrically robust SeC architecture, previously limited to point interactions, with a text-prompting adapter and leverage its temporal memory, so that the target is held through disappearance without drifting to distractors and kept whole even when it fills the entire view. For discovery, the verification layer combines high-speed visual embedding matching with conditional VLM refinement, invoking semantic reasoning only for ambiguous candidates, which filters out the ontological errors that visual-only models cannot distinguish while keeping latency low. Designed with 3D reconstruction in mind, where a single misclassified distractor corrupts the asset, ENEAS unlocks high-quality semantic tracking and segmentation of video, of broad libraries, and of collections of temporally or spatially unordered data, together with the discrimination to tell true instances from their doppelgangers: things that look alike but are not the same. The code and models are available at https://github.com/speridlabs/eneas
Mirrors are common in real-world images, yet producing geometrically consistent reflections with generative models remains challenging. Unlike most objects, mirror appearance depends on scene geometry and viewpoint, making it hard to synthesize using learned appearance priors alone. We address this in the mirror inpainting setting, where the scene is fixed and only the mirror region is generated. Our key insight is that much mirror content is geometrically constrained by the visible scene and need not be hallucinated. We estimate scene geometry and project visible content into the mirror to recover reflection regions determined by geometry. A generative model then completes the mirror region via a two-mask diffusion strategy balancing geometric constraints with the model's learned priors, reducing projection artifacts and improving reflection consistency. The method is training-free and applicable to complex real-world scenes. We evaluate on MirrorBench-V2 (synthetic) and real images. Using standard and geometry-aware metrics, we show that explicitly using scene geometry improves consistency.
Sobhan Asasi, Ozge Mercanoglu Sincan, Richard Bowdencs.CV
Sign language dictionaries are essential resources for sign language learners, yet automatically retrieving a sign from a dictionary, given only a query video, remains a challenging problem due to the natural variability between signers. Existing sign representation learning methods are built for closed-set recognition, producing embeddings that do not generalise to the open-set, signer-independent setting that retrieval demands. \textbf{SignSeek} closes this gap by contrastively learning sign representations with saliency-guided articulator masking. A contrastive objective aligns same-gloss signs across signers, while our Articulator Saliency-Guided Masking (ASGM) pinpoints the single most critical articulator per sign. This drives two complementary objectives, a masked contrastive alignment (MAC) loss that sees the sign through a single articulator and a masked prediction (MAP) loss that reconstructs it in latent space from the surrounding spatio-temporal context. Pretrained on 266K samples ($\sim$5,700 glosses) across multiple sign languages, \textbf{SignSeek} sets a new state-of-the-art performance in cross-corpus retrieval on ASL-Citizen, WLASL, and NMFs-CSL without any downstream fine-tuning. Strikingly, it achieves zero-shot generalisation to an entirely unseen British Sign Language (BSL), surpassing methods explicitly trained on BSL, and transfers seamlessly to isolated sign recognition and subtitle alignment, outperforming prior skeleton-based methods.
Paul Büschl, Ezequiel de la Rosa, Julia Wolleb +3cs.CV
Implicit neural representations (INRs) can model continuous 3D shapes with a shared coordinate decoder and per-instance latent codes. At test time, autodecoder-style models commonly freeze the decoder and optimize a new latent code from sparse off-grid SDF samples. When these samples underconstrain inference, the latent can drift toward regions that fit the observations but decode implausible unobserved geometry. We propose a post-hoc observation-conditioned latent energy prior for frozen INR decoders. The energy scores standardized latents conditioned on a permutation-invariant encoding of the sparse observation set and is used as a residual expert alongside an L2 latent prior selected on validation data. We evaluate on a controlled cell-nucleus SDF dataset and a public MedShapeNet-derived SDF completion dataset. The proposed L2 objective augmented with conditional energy improves consistently over a validation-selected L2 baseline in the sparsest cell-nucleus regimes and, on MedShapeNet, outperforms both L2 and a six-component GMM latent-density prior across all reported readouts. A shuffled-context ablation is consistently weaker than matched context, supporting an observation-specific contribution. These results suggest that lightweight conditional energies can make pretrained INR decoders more observation-aware without retraining.
Pairwise preference labels rank complete images, yet Diffusion-DPO applies their effect over many spatial and denoising-time coordinates. For attention-based, noise-prediction latent diffusion, ToPO (Token-Oriented Preference Optimization) constructs a per-minibatch, detached, separable spatial-temporal route from branchwise squared-residual contrast in a frozen reference denoiser. Preferred-branch cross-attention uses content tokens to modulate the spatial factor, and an auxiliary pixel-midpoint ordering term is added without local labels or a learned reward model. In matched three-seed retrainings with a shared update schedule, ToPO has higher endpoint estimates than Diffusion-DPO on all five reported SD-1.5 metrics and on HPSv2, ImageReward, and CLIP for SDXL. It also receives larger raw win shares in an aggregate blind SDXL A/B study. These findings are scoped to the reported equal-update U-Net protocols rather than an equal-compute comparison.
Patrick Zimmer, Michael Halstead, Chris McCoolcs.CV cs.RO
Labelling vision datasets, especially for segmentation tasks, is a laborious and costly process that stymies novel developments in agricultural robotics. In this paper, we present DropClick, a click-guided segmentation tool that simplifies the annotation process. Our system utilises single-click inputs on objects to generate pseudo-labels, which can replace manual annotations. DropClick stands out as it is a semi-automated approach and does not require a click for every object in the scene. It can therefore further reduce the required amount of user input drastically. We evaluate our method on two challenging agricultural robotic datasets, SB20 and BUP20 for plant and fruit segmentation, respectively. DropClick is first trained on a small subset of just 5 images from the original training data. This DropClick model can then be deployed as a one-click segmentation system and achieves comparable or higher performance than other one-click methods achieving an mIoU of 70.0 and 72.6 points, for SB20 and BUP20 respectively. DropClick then excels at maintaining high performance when clicks are not given (e.g. dropped); when 50% of the clicks are missing it still maintains an mIoU of 68.9 and 71.3 points, for SB20 and BUP20 respectively. We validate DropClick as a pseudo-labelling approach by taking its outputs to train a Mask2Former instance-based segmentation model in a semi-supervised manner. In this process, partially removing user input from DropClick yields similar high performance when compared to providing all clicks, at 70.1 vs 70.7 points AP50 for SB20 and no difference for BUP20 at 77.0 for both models; at the same time saving 46.3% of total input for SB20 and 31.9% for BUP20.
Julian Truetsch, Felix Hauser, Christoph Stiller +1cs.CV cs.CL cs.LG cs.NE cs.RO
Understanding the composition of large-scale autonomous driving datasets is essential for safety, robustness, and reliable operation across domains. For example, domain shift between locations could lead to the operating environment being misaligned with the training data, resulting in potentially dangerous performance degradation. Yet, existing data analysis pipelines largely rely on metadata, predefined labels, or manual inspection, which provide limited semantic insight or do not scale. This paper studies set difference captioning: given two subsets of images, the goal is to produce a natural-language hypothesis describing differences between the target and reference set. Building on a two-stage formulation, we adapt the method to autonomous driving by focusing on object-centric patches derived from object detection, which simplifies aggregation and enables attribution of differences to specific object instances or categories. To evaluate this setting in-domain, we introduce a new benchmark, AD-Diff Bench. Low-concentration experiments assess the suitability of set-difference-captioning approaches to sparse, real-world differences. We restrict our experiments to open-weight models to support reproducibility and ease of deployment. The proposed benchmark and analysis provide a step towards practical, human-interpretable dataset introspection for autonomous driving datasets. Our implementation and benchmark dataset are available at https://github.com/KIT-MRT/AD-Diff