Referring surgical video segmentation requires segmenting a target instrument or tissue region across video frames according to a natural language expression. Recent Segment Anything Model 2 (SAM2) based two-stage methods (e.g., ReSurgSAM2) first ground the referred target in an initial or selected frame, then propagate the selected mask via tracking. Although effective, their performance is highly sensitive to the quality of the initial grounded mask: once an incorrect anchor is selected, subsequent tracking tends to propagate the error. This issue is especially challenging in surgical videos due to visually similar instruments, occlusion, and complex tissue-tool interactions. To address this issue, we propose ReGround-Surg, a lightweight reliability-guided anchor grounding framework to improve SAM2-based referring surgical video segmentation. It first predicts a text-conditioned spatial reliability map from the referring expression and current-frame visual features. The map is then reused in two complementary branches: a Gated Side Adapter enhances expression-relevant visual regions before text-to-vision fusion, while a Reliability-Weighted Vision-to-Text Attention module suppresses off-target visual evidence during prompt-token aggregation. Experiments on Ref-EndoVis17 and Ref-EndoVis18 show consistent improvements over state-of-the-art methods across three evaluation splits with negligible speed reduction. Code is publicly available at https://github.com/JiaxinWen1/ReGround-Surg.
Video multimodal large language models support language guided video segmentation, but they often show spatio temporal inconsistencies, e.g., jitter, drift, and identity switches. These failures are more common when targets are partly hidden or when similar objects appear nearby.One likely reason is that current training lacks explicit spatial priors, which makes it difficult to maintain stable spatial identity and shape over time. We present PhysMLLMs, a training-stage prior injection architecture that injects physics-inspired spatial continuity priors into Video MLLMs. PhysMLLMs is designed to encourage more stable object-centered representations by aligning the student global visual representation with a frozen teacher model during training. Our core mechanism, Global Representation Prior Alignment (REPA-Global), distills global visual representations from a frozen DINOv2 teacher using an offline embedding cache and a scheduled distillation plan. This design keeps inference unchanged and does not add inference time cost. Across multiple video benchmarks, PhysMLLMs improves video segmentation mask quality and cross-frame consistency, with larger gains on challenging cases involving small targets, fast motion, occlusion, distractors, and reasoning queries. On single-frame referring image segmentation and representative general VLM benchmarks, PhysMLLMs maintains comparable performance, demonstrating that the injected spatial prior improves video consistency without compromising image-level grounding or general multimodal capability. These results suggest that physics-inspired spatial prior injection can improve temporal stability while preserving general capability. The code is available at https://github.com/tusu-code/20260121-icml2026-2.git.
Simultaneously reconstructing and understanding 3D environments is essential for embodied agents. Toward this goal, feed-forward semantic 3D Gaussian Splatting (3DGS) efficiently constructs semantic scene representations from sparse multi-view observations. However, existing methods lack explicit instance discrimination and mainly support category- or phrase-based semantic queries. To this end, we propose GroupForward, an instance-grouped feed-forward Gaussian splatting model that reconstructs geometry, appearance, instance structure, and semantics from sparse, unposed, and uncalibrated multi-view images. Unlike existing methods that attach high-dimensional semantic features to each Gaussian, GroupForward learns compact instance embeddings that group Gaussians into cross-view consistent 3D instances, reformulating feed-forward semantic 3DGS from per-Gaussian semantic feature rendering to instance-level semantic aggregation and propagation. Building on these instance groups, we further propose a Referential Scene Reasoning Framework (RSRF) for complex 3D referring segmentation. RSRF constructs an instance-grouped 3D scene graph and retrieves candidate instances for a given referring expression. A vision-language model then reasons over structured instance evidence and multi-view observations to identify the referred instance among the candidates. RSRF thereby extends language interaction from simple semantic querying to complex referential scene reasoning. Experiments on semantic reconstruction and referential reasoning demonstrate the effectiveness of our instance-grouped reconstruction and reasoning framework.
This report presents a two-stage, training-free solution for the MeViS-Text track of the 8th LSVOS Challenge. The task requires a model to localize and segment the object specified by a natural-language expression throughout a video. Such expressions often depend on temporal cues, including actions, interactions, directions, and relative positions. Our first stage uses Gemini-3.1 Pro via API to decompose a video-level event into instance-level targets, select a key frame for each target, and generate a discriminative description aligned with that frame. In the second stage, SAM3-agent produces a pixel-level seed mask on the selected frame, and the SAM3 video tracker propagates the mask bidirectionally through the video. Valid instances are grounded and propagated independently before their frame-wise masks are merged. All local SAM3 processing runs on a single NVIDIA GeForce RTX 4090 without task-specific training or model ensembling. Our method ranked third on the challenge test set, obtaining J&F, J, F, N-acc., T-acc., and Final scores of 0.761, 0.7367, 0.7852, 0.8333, 0.9755, and 0.856593, respectively.
Referring Video Object Segmentation (RVOS) aims to segment referred objects at the pixel level in video sequences based on natural language descriptions. Existing methods typically introduce motion information within a unified cross-modal temporal modeling framework, where language cues are used for target localization and segmentation. However, the dependency of expressions on motion semantics is not explicitly modeled, making it difficult to adaptively adjust the use of motion information according to different semantic requirements. To address these issues, we propose an Expression-driven Motion Calibration (EMC) framework for RVOS that explicitly unlocks and leverages the motion semantics within expressions. The proposed method extracts interpretable motion control signals from expressions via a Motion Signal Processing (MSP) module, and employs a Motion Influence Calibration (MIC) module to adjust the contribution of motion cues during temporal decision making. In addition, a Semantic Temporal Stage Construction (STSC) module is introduced to build expression-relevant temporal stages, providing a compact temporal candidate space for motion calibration. Through extensive evaluation on six standard benchmarks, including Ref-YouTubeVOS, Ref-DAVIS17, MeViS (valid/valid$^u$), A2D-Sentences, and JHMDB-Sentences, the superiority of our method is validated. We will release the code on https://github.com/Jeven7/EMC.
Open-vocabulary referring segmentation in 3D Gaussian Splatting (3DGS) requires a neural model to select Gaussian primitives according to free-form language expressions. Existing 3DGS-based methods usually rely on global text-region similarity, which is weak for queries involving attributes, reference objects, spatial relations, and fine-grained parts. This often causes target-reference confusion, granularity mismatch, part-whole leakage, and relation violations. We propose QAGaussian, a query-adaptive neural reasoning framework for language-guided Gaussian primitive selection. QAGaussian first learns query-conditioned multi-scale Gaussian slots as differentiable candidates whose receptive fields are shaped by the input expression. It then builds a relation-aware slot graph with language-conditioned edge weighting to propagate target-reference, attribute, part-whole, and contextual evidence. A granularity-adaptive router softly combines region-level, object-level, part-level, attribute-aware, and relation-aware mask branches, followed by relation-constrained refinement for spatial, part-whole, attribute, and geometric consistency. QAGaussian is pretrained only on Mosaic3D-5.6M for Gaussian-text alignment and evaluated on independent benchmarks without target-dataset fine-tuning. It achieves 47.2 Avg. mIoU and 63.2 Avg. F1, outperforming the strongest 3DGS referring baseline by 2.7 mIoU points and 2.9 F1 points. It also improves Part-mIoU from 38.6 to 43.4, Rel-mIoU from 44.4 to 50.8, and reduces target-reference confusion from 10.8 to 7.4. These results demonstrate that query-conditioned slot learning, relation-aware graph reasoning, and adaptive routing provide an effective neural modeling strategy for open-vocabulary referring segmentation in 3DGS. The code is available at https://github.com/zqeslwyz/QAGaussian.
Referring remote sensing image segmentation (RRSIS) aims to delineate targets specified by natural language expressions in remote sensing imagery. Existing methods mainly follow joint fusion segmentation (JFS) or decoupled prompt segmentation (DPS). JFS is efficient but often suffers from limited accuracy because referent localization and mask delineation are optimized under a unified objective, whereas DPS separates localization from mask generation using spatial prompts and foundation segmenters at the cost of higher memory consumption and inference latency. To bridge this gap, we propose DiCoR, a decoupled referent disambiguation and contour recalibration framework built on an efficient JFS pipeline. DiCoR addresses two key challenges: distinguishing the correct referent from ambiguous candidates and refining coarse masks after localization. A disambiguation-aware localization guidance strategy ranks salient candidate regions with adaptive linguistic cues and injects the resulting localization prior into fused features. A lightweight contour recalibration module further predicts residual corrections to coarse logits under localized contour supervision, improving mask quality with limited computational overhead. Experiments on RefSegRS, RRSIS-D, and RISBench show that DiCoR achieves the best segmentation accuracy across all three benchmarks. On RefSegRS, it improves mIoU and gIoU by 5.28% and 2.87% over a competitive JFS method while running 4.7% faster than a representative DPS method, demonstrating a favorable accuracy-efficiency trade-off. Code is available at https://github.com/zyGao1126/DiCoR.
Part-level affordance grounding has advanced the localization of functional object regions associated with elemental actions. Extending this capability to complex tasks calls for connecting the semantic roles of participating objects with task-state-aligned visual observations and multi-step planning. We introduce EgoAfford, a benchmark designed to connect these three aspects. Given an egocentric observation and a high-level tabletop task, a model must generate the remaining plan and segment the functional regions of up to three components of the next action: the direct object, instrument, and destination. EgoAfford comprises approximately 15.5k human-verified images from 2,000 generated multi-step scenes, organized as semantically aligned, task-complete image series, together with EgoAfford-Real, 102 manually captured images spanning 26 tasks. We further present EgoLens, a 3B multimodal large language model with role-specific mask decoders, as an in-domain reference model for this joint task. Evaluations of recent referring-segmentation MLLMs, commercial-VLM--SAM2 pipelines, and EgoLens highlight the complementary challenges of next-step inference and action-role-conditioned part grounding. EgoLens establishes strong reference performance on both generated and manually captured observations. Together, EgoAfford and EgoLens provide a foundation for jointly studying perception and planning in multi-step tabletop tasks. Our project page is available at: https://egoafford.github.io
Referring Remote Sensing Image Segmentation (RRSIS) has achieved significant progress through the integration of VLMs and the Segment Anything Model (SAM). However, this progress largely relies on strong pre-trained capabilities, while leaving two fundamental limitations insufficiently addressed: (1) Architectural Weak-Coupling, where the unidirectional flow forces reliance on coarse VLM prompts and wastes SAM's pixel-level structural guidance, causing localization drift; and (2) Object-Centric Semantic Bias, where models overemphasize dominant object semantics while remaining insensitive to spatial reasoning crucial for RRSIS. Motivated by these observations, we propose CROSS, a tightly integrated paradigm for RRSIS. First, we introduce Linguistic-Guided Cascaded Distillation (LGCD) to bridge the architectural gap, which distills SAM's geometric affinities as soft regularizers into VLM intermediate layers, injecting dense structural priors to refine localization. Second, Perspective-Spatial Contrastive Learning (PSCL) imposes cross-anchored constraints by mining mask-filtered deceptive distractors and spatial-linguistic counterfactuals as hard negatives, explicitly shattering semantic shortcuts to enforce genuine logical consistency. Extensive experiments on RRSIS benchmarks demonstrate that CROSS achieves state-of-the-art performance and maintains precise localization even under severe spatial description perturbations, standing as a robust new paradigm for RRSIS.
MLLM-based segmentation faces a core segmentation trilemma: high segmentation performance, preserved dialogue ability, and fast inference. Embedding-prediction methods may disrupt language modeling through pixel-level objectives, whereas next-token generation is inefficient for dense masks. We propose All-Mask Prediction, decoupling autoregressive dialogue from non-autoregressive mask prediction. Its binary instantiation, STAMP (Simultaneous Textual All-Mask Prediction), emits an in-vocabulary <SEG> trigger, fuses image-aligned mask tokens with corresponding patch features, and uses hybrid attention to classify all tokens as foreground or background in one pass. It thereby combines strong referring and reasoning segmentation with preserved multimodal ability and efficient inference. However, binary masks cannot retain multiple semantic or instance identities without repeated target-specific predictions. We therefore propose Structured All-Mask Prediction and develop STAMPlus. It generates a target list with explicit IDs and optional boxes, binds these IDs to a shared multi-class mask space, and jointly predicts all targets in one non-autoregressive pass. A single unified checkpoint retains STAMP's referring and reasoning capabilities while extending to open-vocabulary semantic, instance-aware, and remote-sensing small-target segmentation, where high-resolution mask-token scaling preserves finer spatial evidence. Across these settings, STAMPlus achieves state-of-the-art segmentation performance, preserves general multimodal instruction following, and reduces 12-category latency from 13.50s for repeated STAMP inference to 5.16s. Further analyses show that accurate target cues improve segmentation and learned spatial grounding benefits look-twice reasoning. Overall, STAMPlus resolves the trilemma beyond single-target prediction.
Referring video object segmentation (RVOS) requires segmenting a target specified by natural language throughout a video. Recent agentic approaches combine multimodal large language models with promptable segmentation models to perform RVOS without task-specific training. However, most pipelines rely on one-shot spatial grounding followed by mask propagation, leaving both the initial prompts and temporal predictions largely unverified. We introduce ReflexTrack, a training-free, feedback-driven agent that closes this loop at both spatial and temporal levels. Mask-guided Spatial Refinement evaluates the mask induced by the current keyframe prompt and iteratively updates the bounding box together with positive and negative points, yielding a more reliable initialization. Video-level Mask Reflection assesses the complete mask sequence, localizes unreliable intervals, selects complementary repair keyframes, and generates candidate predictions through mask-guided re-propagation. Only candidates that provide a verified improvement are used to update the affected intervals, preserving reliable predictions elsewhere. All components remain frozen during inference. ReflexTrack achieves an overall $\mathcal{Q}$ score of $69.7$ on Ref-VPS and a $\mathcal{J}\&\mathcal{F}$ score of $67.2$ on ReasonVOS. These results demonstrate that prediction-level feedback substantially improves the reliability of training-free RVOS.
Penglei Sun, Yehua Huang, Zhuoli Tao +8cs.CV cs.AI
Language-guided aerial perception aims to understand user-specified tiny targets in complex unmanned aerial vehicle (UAV) scenes. In real UAV deployment, the UAV must respond while it flies, so such perception runs in an online streaming manner, where frames arrive sequentially and the model responds to each one without access to future frames. However, applying current Multimodal Large Language Models (MLLMs) to this setting raises two challenges. First, targets viewed from the air are often tiny, yet the visual compression in existing MLLMs treats all regions equally and discards their fine-grained details. Second, understanding a continuous stream requires past-frame context, yet retaining the entire history is infeasible on resource-constrained onboard hardware, whereas discarding it causes the target to drift or disappear. We address the tiny object and streaming challenges from both data and method perspectives. From the data perspective, we present \textbf{DroneEyes}, the \textbf{first} pixel-level and open-vocabulary referring-segmentation dataset for tiny aerial targets, comprising $2,140$ high-definition videos and $176,623$ pairs across Object Description and Referring Expression tasks, with dense per-frame masks. From the method perspective, we propose \textbf{SkyAnchor}, an MLLM with two designs to the above challenges: a Semantics-Aware Token Router that preserves small-target under a reduced visual-token budget, and a Hierarchical Memory Bank that keeps the target consistently understood on streams.
Recent advancements in 3D Gaussian Splatting (3DGS) have enabled language-guided scene understanding. However, existing Referring 3D Gaussian Splatting (R3DGS) methods are fundamentally restricted to single-target queries. To reflect the ambiguity of real-world instructions, we introduce the Generalized Referring 3D Gaussian Splatting Segmentation (GR3DGS) task, which requires dynamically segmenting an arbitrary number of targets (0, 1, or $N$). To facilitate comprehensive evaluation of this new task, we construct two new benchmarks: GR-LERF and GR-ScanNet. Crucially, existing R3DGS paradigms exhibit fundamental technical bottlenecks that severely limit their performance on the GR3DGS task: they lack intrinsic 3D point-level understanding by operating merely on 2D rendered pixels, and they incur prohibitive computational overhead by requiring per-scene optimization to embed heavy semantic features. To dismantle these bottlenecks, we propose ZeroSplat, a novel training-free and zero-feature framework. ZeroSplat lifts 2D Vision-Language Model (VLM) priors into 3D space through robust multi-view geometric constraints. This strategy enables intrinsic point-level understanding without incurring any additional feature storage. Extensive experiments demonstrate that ZeroSplat significantly outperforms state-of-the-art methods across generalized and single-target scenarios while maintaining exceptional efficiency. Project Page: https://inkmind-ai.github.io/ZeroSplat
Referring Camouflaged Object Detection (Ref-COD) requires segmenting hidden targets guided by reference cues. While supervised methods are annotation-heavy and training-free approaches via sparse point-prompting are sensitive to localization errors, we propose GFR-SAM, a robust three-stage training-free framework. GFR-SAM shifts the paradigm from fragile point-matching to a "Generate-Filter-Refine" pipeline. First, we introduce In-Context Exemplar-guided Segmentation, empowering SAM3 with cross-image inference to generate candidate masks via holistic visual exemplars, bypassing its native intra-image constraints. Second, a Region-Global Contrastive Filtering module ranks candidates through DINOv3-based prototypical alignment, effectively suppressing background distractors. Finally, a Geometric-Semantic Refinement module synergizes bounding box and text prompts to recover fine-grained boundaries and enhance instance recall. Evaluated on the R2C7K benchmark, GFR-SAM outperforms existing training-free methods by 8.7\% in weighted F-measure ($F_β^w$) and competes with supervised state-of-the-art counterparts. Ultimately, this work underscores the potential of unlocking SAM3's latent capability for cross-image In-Context prompting, establishing a robust, training-free paradigm that effectively bridges the gap between general-purpose foundation models and specialized, label-intensive perception tasks without the need for task-specific fine-tuning.
Referring remote sensing image segmentation isolates the object named by a natural-language expression in an aerial image. Existing training-free methods resolve the expression through implicit vision-language activations or region-text similarity, which gives weak control over the spatial, comparative, and ordinal relations that dominate aerial referring: they cannot represent constructions such as the largest ship or the second court from the left. We propose GeoSelect, a training-free pipeline that reframes referring as the execution of a typed spatial program. A frozen, text-only language model synthesises the expression into a small domain-specific language, a well-formedness checker accepts the program, and a deterministic executor runs it. The central abstraction is a single scored candidate set type under which every operator composes: continuous geometric fields realise position and proximity as dense pixel-level maps, while discrete set and order operators add the extremum, ordinal, counted-union, and relational constructions that fields alone cannot express. Because execution is explicit, every intermediate program, field, and ranking is inspectable, and a reliability ladder degrades any failing program to a field-only special case, so every expression returns an answer. GeoSelect attains 58.86 mIoU on RRSIS-D test and 55.27 mIoU on RISBench test, more than twice the best prior training-free method on RRSIS-D, with no referring supervision and on a single GPU. A controlled comparison with candidates and segmenter fixed attributes the gain to explicit execution, not the backbone; an oracle decomposition localises the residual gap to detection recall on RRSIS-D and selection on RISBench, and an exposure audit confirms robustness to pretraining leakage. Code will be released upon acceptance at the project page https://avalon-s.github.io/GeoSelect/.
Existing referring segmentation models passively process static images captured from fixed perspectives, limiting their applicability in Embodied AI, where agents must perform active perception in the continuous 360$^\circ$ environments. To bridge this gap, we introduce a novel task: Active Panoramic Referring Segmentation (APRS). In this setting, an agent is required to adjust its viewing direction ($Δθ, Δφ$) to explore the 360$^\circ$ environment, seeking the object specified by a user instruction for segmentation. To tackle this challenging task, we propose PanoSeeker, a memory-augmented agent for efficient APRS. Rather than relying on heuristic scanning, PanoSeeker integrates a Vision-Language Model (VLM) with EgoSphere, an explicit spatial visual memory. By progressively integrating sequential local observations into a unified 360$^\circ$ representation, EgoSphere enables the agent to plan efficient and non-redundant search trajectories. Once the target is found, the agent performs active viewpoint alignment and outputs the segmentation mask. Furthermore, we curate an expert-annotated search trajectory dataset with memory timelines for Supervised Fine-Tuning, followed by Reinforcement Learning post-training to explicitly optimize PanoSeeker's exploration efficiency. Extensive experiments on our newly established APRS benchmark demonstrate that PanoSeeker achieves superior search efficiency and segmentation accuracy, significantly outperforming adapted state-of-the-art baselines.
This paper explores multi-turn visual reasoning and observes that MLLMs repeatedly fail to localize the target, leading to long, redundant trajectories. We attribute this failure to the entanglement of reasoning and perception within a single model, the MLLM reasons and localizes simultaneously, and inaccurate localization triggers additional reasoning turns that bloat the trajectory. To solve this problem, we propose PixelEyes, a multi-turn visual reasoning agent that explicitly decouples reasoning from perception, i.e., the reasoner decides what to look for, while a specialized perception tool answers where it is. Specifically, PixelEyes introduces 1) Mask-guided Visual Search. A referring segmentation model is invoked to provide mask-precise localization, freeing the reasoner from the need to compensate for imprecise grounding. 2) Semantic-region Breadth-first Search (BFS). To eliminate redundant loops caused by repeatedly cropping incorrect sub-regions, we organize exploration as a breadth-first search over semantic regions. To internalize these capabilities, we construct the PixelEyes-6K dataset by resynthesizing expert trajectories from existing data. This explicitly embeds our mask-guided search and BFS logic into the model. We further introduce Pinpoint-Bench, a zero-hint visual search benchmark, i.e., no location cues are provided in the question, with instance-level masks and bounding boxes that separate localization failures from reasoning failures, enabling fine-grained analysis of failure modes such as inattentional blindness. Recent state-of-the-art MLLMs and visual reasoning agents leave large headroom on Pinpoint-Bench, demonstrating its quality and difficulty. Code and models are open-sourced.
Referring Remote Sensing Image Segmentation (RRSIS) seeks to localize and segment the target object or region specified by a natural language expression in a remote sensing image. While existing RRSIS models have benefited from large-scale foundation models, they predominantly rely on full fine-tuning. These approaches are computationally intensive and may weaken the generalization ability of pre-trained models, as extensive fine-tuning on significantly smaller downstream datasets can distort the well-structured feature representations learned during large-scale pre-training. Although Parameter-Efficient Tuning (PET) offers a potential alternative, existing PET frameworks primarily focus on single-modal optimization, failing to capture the complex cross-modal dependencies required for multimodal reasoning, while simultaneously struggling to bridge the substantial domain gap between natural scenes and aerial imagery. To address these limitations, we propose a novel framework, Semantic-driven Scale and Spatial Selection for Efficient Cross-modal Alignment (S4ECA), which enables effective and efficient cross-modal interaction through parameter-efficient adaptation. Specifically, we design a dual-encoder adapter architecture. The textual adapter employs learnable queries to distill highly semantic language proxies from word-level embeddings, facilitating early grounding. Simultaneously, the visual adapter refines hierarchical feature representations through a multi-scale dense extractor, followed by a language-guided scale and spatial selection mechanism that dynamically emphasizes relevant visual contexts, ensuring precise cross-modal alignment. By updating only 2.4% of the backbone parameters, our proposed model achieves state-of-the-art performance on the RRSIS-D and RefSegRS datasets, demonstrating superior efficiency and precision in complex aerial scenarios.
Recent advances in 3D multimodal large language models (3D-MLLMs) have enabled unified solutions for 3D scene understanding tasks, including visual question answering, captioning, and referring segmentation. However, existing 3D-MLLMs remain largely object-centric, limiting their ability to model fine-grained part structures that are essential for embodied interaction with 3D environments. In this work, we present PAR3D, a unified part-aware 3D-MLLM framework that enables models to understand, reason about, and ground both objects and their parts in 3D scenes. To enable training and evaluation of part-aware 3D scene understanding, we introduce ScenePart, a synthetic 3D scene dataset with part-level annotations and language instructions. We further develop Part-Aware 3D Representation Learning to enrich 3D visual representations with fine-grained part-level semantics, and propose Hierarchical Segmentation Query Generation to ground part targets via hierarchical object-part queries. Extensive experiments show that our method substantially improves part-level question answering and referring segmentation, while also achieving strong performance across object-level vision-language tasks.