论文检索

Yousef Yeganeh, Goktug Guvercin, Nassir Navab, Azade Farshad

While conventional computer vision emphasizes pixel-level and feature-based objectives, medical image analysis of intricate biological structures necessitates explicit representation of their complex topological properties. Despite their successes, deep learning models often struggle to accurately capture the connectivity and continuity of fine, sometimes pixel-thin, yet critical structures due to their reliance on implicit learning from data. To address this challenge, we introduce Conformable Convolution, a novel convolutional layer designed to explicitly impose topological consistency. Conformable Convolution learns adaptive kernel offsets that focus on regions of high topological significance within an image. This prioritization is guided by our proposed Topological Posterior Generator (TPG) module, which leverages persistent homology. The TPG module identifies key topological features and guides the convolutional layers by applying persistent homology to feature maps transformed into cubical complexes. Unlike existing approaches that are merely aware of topology, our method explicitly constrains the learning process to ensure topological correctness. The proposed modules are architecture-agnostic, enabling them to be integrated seamlessly into various architectures. We showcase the effectiveness of our framework in the segmentation task, where preserving the interconnectedness of structures is critical. The results on three diverse datasets demonstrate that our framework effectively preserves the topology both quantitatively and qualitatively.

Kai Ye, YingShi Luan, Zhudi Chen, Guangyue Meng, Pingyang Dai, Liujuan Cao

Referring Image Segmentation (RIS), which aims to segment specific objects based on natural language descriptions, plays an essential role in vision-language understanding. Despite its progress in remote sensing applications, RIS under Low-Altitude Drone (LAD) scenarios remains underexplored, as existing datasets and methods are typically designed for high-altitude and static-view imagery. They struggled to handle the unique characteristics of LAD views, such as diverse viewpoints and high object density. In this paper, we propose RIS-LAD, the first fine-grained RIS benchmark tailored for LAD scenarios, featuring 13,871 meticulously annotated image-text-mask triplets collected from real-world drone footage with emphasis on small, densely cluttered objects and multi-view perspectives. Additionally, we propose the Semantic-Aware Adaptive Reasoning Network, which decomposes and adaptively routes semantic information to different network stages rather than uniformly injecting all linguistic features. Specifically, the Category-Dominated Linguistic Enhancement aligns visual features with object categories during early encoding, while the Adaptive Reasoning Fusion Module dynamically selects semantic cues across scales to enhance reasoning in complex scenes. Extensive experiments reveal that RIS-LAD presents substantial challenges to state-of-the-art RIS algorithms, and also demonstrate the effectiveness of our proposed model in addressing these challenges.

Yanwu Yang, Guinan Su, Jiesi Hu, Francesco Sammarco, Jonas Geiping, Thomas Wolfers

Universal medical image segmentation models have emerged as a promising paradigm due to their strong generalizability across diverse tasks, showing great potential for a wide range of clinical applications. This potential has been partly driven by the success of general-purpose vision models such as the Segment Anything Model (SAM), which has inspired the development of various fine-tuned variants for medical segmentation tasks. However, fine-tuned variants like MedSAM are trained on comparatively limited medical imaging data that often suffers from heterogeneity, scarce annotations, and distributional shifts. These challenges limit their ability to generalize across a wide range of medical segmentation tasks. In this regard, we propose MedSAMix, a training-free model merging method that integrates the strengths of both generalist models (e.g., SAM) and specialist models (e.g., MedSAM) for medical image segmentation. In contrast to traditional model merging approaches that rely on manual configuration and often result in suboptimal outcomes, we propose a zero-order optimization method to automatically discover optimal layer-wise merging solutions. Furthermore, for clinical applications, we develop two regimes to meet the demand of domain-specificity and generalizability in different scenarios by single-task optimization and multi-objective optimization respectively. Extensive evaluations on 25 medical segmentation tasks demonstrate that MedSAMix effectively mitigates model bias and consistently improves performance in both domain-specific accuracy and generalization, achieving improvements of 6.67% on specialized tasks and 4.37% on multi-task evaluations.

Rui Yang, Yunfei Bai, Yuehua Liu, Xiaomao Li, Shaorong Xie

In semi-supervised semantic segmentation (SSSS), segmentation performance is heavily constrained by the quality of pseudo labels. However, prevalent pseudo-label optimization approaches rely on the model’s internal self-correction. When the model fails to recognize or adequately represent certain classes, this self-enhancement mechanism amplifies initial mistakes, ultimately leading to poor semantic or spatial consistency. To address this limitation, we propose ViLaDiff to enhance pseudo-label quality. Specifically, ViLaDiff first employs a prompt-guided image captioning task to generate descriptive text for each input image, providing high-level semantic context. To our knowledge, this is the first attempt to introduce vision-language modeling into SSSS. We design a vision-language fusion module to enhance feature semantics and discriminative capability. It integrates cross-modal interactions with dual-path knowledge to ensure semantic consistency. Additionally, while language provides high-level semantic guidance, it is inherently limited in expressing fine-grained spatial structures. Therefore, we propose an edge-aware mixed-noise diffusion process. It simulates feature-level uncertainty through Gaussian perturbations and introduces class-flipping noise into the masks to model misclassification errors. To enhance boundary refinement, we apply a higher flipping probability along mask edges, enabling edge-aware modeling during denoising. Extensive experiments on public benchmarks validate that our method significantly improves pseudo-label quality and segmentation performance.

An Yang, Chenyu Liu, Jun Du, Jianqing Gao, Jia Pan, Jinshui Hu, Baocai Yin, Bing Yin, Cong Liu

3D Gaussian Splatting (3D-GS) has emerged as an efficient 3D representation and a promising foundation for semantic tasks like segmentation. However, existing 3D-GS-based segmentation methods typically rely on high-dimensional category features, which introduce substantial memory overhead. Moreover, fine-grained segmentation remains challenging due to label space congestion and the lack of stable multi-granularity control mechanisms. To address these limitations, we propose a coarse-to-fine binary encoding scheme for per-Gaussian category representation, which compresses each feature into a single integer via the binary-to-decimal mapping, drastically reducing memory usage. We further design a progressive training strategy that decomposes panoptic segmentation into a series of independent sub-tasks, reducing inter-class conflicts and thereby enhancing fine-grained segmentation capability. Additionally, we fine-tune opacity during segmentation training to address the incompatibility between photometric rendering and semantic segmentation, which often leads to foreground-background confusion. Extensive experiments on multiple benchmarks demonstrate that our method achieves state-of-the-art segmentation performance while significantly reducing memory consumption and accelerating inference.

Zhonghao Yan, Muxi Diao, Yuxuan Yang, Ruoyan Jing, Jiayuan Xu, Kaizhou Zhang, Lele Yang, Yanxi Liu, Kongming Liang, Zhanyu Ma

Accurately grounding regions of interest (ROIs) is critical for diagnosis and treatment planning in medical imaging. While multimodal large language models (MLLMs) combine visual perception with natural language, current medical-grounding pipelines still rely on supervised fine-tuning with explicit spatial hints, making them ill-equipped to handle the implicit queries common in clinical practice. This work makes three core contributions. We first define Unified Medical Reasoning Grounding (UMRG), a novel vision–language task that demands clinical reasoning and pixel-level grounding. Second, we release U-MRG-14K, a dataset of 14K samples featuring pixel-level masks alongside implicit clinical queries and reasoning traces, spanning 10 modalities, 15 super-categories, and 108 specific categories. Finally, we introduce MedReasoner, a modular framework that distinctly separates reasoning from segmentation: an MLLM reasoner is optimized with reinforcement learning, while a frozen segmentation expert converts spatial prompts into masks, with alignment achieved through format and accuracy rewards. MedReasoner achieves state-of-the-art performance on U-MRG-14K and demonstrates strong generalization to unseen clinical queries, underscoring the significant promise of reinforcement learning for interpretable medical grounding.

Zishan Xu, Yifu Guo, Yuquan Lu, Fengyu Yang, Junxin Li, Lihua Cai

Traditional video reasoning segmentation methods rely on supervised fine-tuning, which limits generalization to out-of-distribution scenarios and lacks explicit reasoning. To address this, we propose VideoSeg-R1, the first framework to introduce reinforcement learning into video reasoning segmentation. It adopts a decoupled architecture that formulates the task as joint referring image segmentation and video mask propagation. It comprises three stages: (1) A hierarchical text-guided frame sampler to emulate human attention; (2) A reasoning model that produces spatial cues along with explicit reasoning chains; and (3) A segmentation-propagation stage using SAM2 and XMem. A task difficulty-aware mechanism adaptively controls reasoning length for better efficiency and accuracy. Extensive evaluations on multiple benchmarks demonstrate that VideoSeg-R1 achieves state-of-the-art performance in complex video reasoning and segmentation tasks.

Xingguo Xu, Zhanyu Liu, Weixiang Zhou, Yuansheng Gao, Junjie Cao, Yuhao Wang, Jixiang Luo, Dell Zhang

Multi-modal object Re-Identification (ReID) aims to exploit complementary information from different modalities to retrieve specific objects. However, existing methods often rely on hard token filtering or simple fusion strategies, which can lead to the loss of discriminative cues and increased background interference. To address these challenges, we propose STMI, a novel multi-modal learning framework consisting of three key components: (1) Segmentation-Guided Feature Modulation (SFM) module leverages SAM-generated masks to enhance foreground representations and suppress background noise through learnable attention modulation; (2) Semantic Token Reallocation (STR) module employs learnable query tokens and an adaptive reallocation mechanism to extract compact and informative representations without discarding any tokens; (3) Cross-Modal Hypergraph Interaction (CHI) module constructs a unified hypergraph across modalities to capture high-order semantic relationships. Extensive experiments on public benchmarks (i.e., RGBNT201, RGBNT100, and MSVR310) demonstrate the effectiveness and robustness of our proposed STMI framework in multi-modal ReID scenarios.

Tianqi Xu, Yashi Zhu, Quansong He, Yue Cao, Kaishen Wang, Zhang Yi, Tao He

Integrating Ordinary Differential Equations (ODEs) with U-shaped neural networks has emerged as a novel direction in medical image segmentation. Current networks predominantly employ discretization methods incorporating ODEs. However, these methods face inherent trade-offs between model compactness, computational accuracy, and efficiency. Continuous ODE solutions were rarely studied because they face three limitations: high computational costs, long training time, and poor generalization ability. To address these limitations, we propose an innovative Continuous Neural Memory ODE UNet (CNM-UNet), which replaces all hierarchical decoder layers in vanilla UNet with a single Continuous Neural Memory ODEs Block (CNM-Block) decoder, significantly reducing computation costs and improving training efficiency. CNM-UNet leverages ODEs' dynamic properties to establish continuous temporal feature extraction. For alleviating the generalization problem, a DUal SElf-updated (DUSE) strategy based on test-time adaptation principles is introduced to enhance cross-domain generalization. Experimental results demonstrate CNM-UNet's comprehensive advantages in computational capacity, convergence speed, and cross-domain adaptability, offering new insights for practical deployment of continuous ODE methodologies for medical image segmentation.

Shijie Xu, Qiulei Dong

Recently, 3D Gaussian Splatting for scene rendering has attracted much attention in computer vision and graphics, but generally suffers from large burdens of both computation and storage when handling large-scale scenes. Some existing works in literature employ a divide-and-conquer strategy for alleviating this issue, where an input large scene is divided into lots of local blocks, and each block is handled separately. However, such a strategy generally leads to limited performance due to the inevitable inconsistency among the 3D Gaussians from different blocks. To address this problem, we propose a Consistent Anchor Guided Gaussian Splatting for large-scale scene rendering under the divide-and-conquer strategy, called CAG-GS. In CAG-GS, a set of learnable anchors for each local block is injected with the corresponding semantic features from a pre-trained semantic segmentation model SAM2 through an explored semantic mapping module, and then these anchors are used to predict the attributes of 3D Gaussians. Moreover, we explore a coarse-to-fine training strategy for CAG-GS, where each local block is optimized independently while being guided by globally consistent semantics. Extensive experimental results on five large-scale scenes demonstrate the superiority of the proposed method over five state-of-the-art methods in most cases.

Junlin Xu, Jincan Li, Feifei Cui, Zhuang Zhang, Jialiang Yang, Shuting Jin, Qiangguo Jin, Yajie Meng

Medical image segmentation plays a crucial role in clinical diagnosis, lesion quantification, and preoperative planning. However, existing Mamba-based architectures, which rely on fixed-direction sequence modeling and flatten images into one-dimensional (1D) sequences, struggle to capture hierarchical anatomical features and spatial dependencies, thereby limiting their representational capacity for complex medical structures. To address these limitations, we propose EccoMamba (Enhanced Cross-hierarchical Continuity Orthogonal Mamba), a U-shaped encoder--decoder framework designed for medical image segmentation. In the encoder's downsampling path, we introduce a Hierarchical Aggregation Enhancement (HAE) module that integrates multi-scale convolutions with hierarchical attention mechanisms. The attention branch further incorporates cross-channel interactions, allowing the model to selectively enhance semantically relevant features while suppressing irrelevant background responses. For skip connections, we design a Structural Continuity Orthogonal (SCO) module to preserve spatial continuity by modeling cross-dimensional dependencies via orthogonal Axial Shifts (AS), thereby mitigating directional bias and improving anatomical consistency. Extensive experiments on four benchmark datasets---ISIC 2018, ISIC 2017, Synapse, and ACDC---show that EccoMamba consistently outperforms state-of-the-art methods in both segmentation accuracy and structural fidelity.

Huihui Xu, Jin Ye, Hongqiu Wang, Changkai Ji, Jiashi Lin, Ming Hu, Ziyan Huang, Ying Chen, Chenglong Ma, Tianbin Li 等

Recent self-supervised image segmentation models have achieved promising performance on semantic segmentation and class-agnostic instance segmentation. However, their pretraining schedule is multi-stage, requiring a time-consuming pseudo-masks generation process between each training epoch. This time-consuming offline process not only makes it difficult to scale with training dataset size, but also leads to sub-optimal solutions due to its discontinuous optimization routine. To solve these, we first present a novel pseudo-mask algorithm, Fast Universal Agglomerative Pooling (UniAP). Each layer of UniAP can identify groups of similar nodes in parallel, allowing to generate both semantic-level and instance-level and multi-granular pseudo-masks within ens of milliseconds for one image. Based on the fast UniAP, we propose the Scalable Self-Supervised Universal Segmentation (S2-UniSeg), which employs a student and a momentum teacher for continuous pretraining. A novel segmentation-oriented pretext task, Query-wise Self-Distillation (QuerySD), is proposed to pretrain S2-UniSeg to learn the local-to-global correspondences. Under the same setting, S2-UniSeg outperforms the SOTA UnSAM model, achieving notable improvements of AP+6.9 on COCO, AR+11.1 on UVO, PixelAcc+4.5 on COCOStuff-27, RQ+8.0 on Cityscapes. After scaling up to a larger 2M-image subset of SA-1B, S2-UniSeg further achieves performance gains on all four benchmarks.

Kangyu Xiao, Zilei Wang, Yixin Zhang, Junjie Li

Few-shot Semantic Segmentation (FSS) aims to segment the novel target objects with the guidance of minimal annotated reference examples. The affinity-based method has great advantages in the FSS inference stage for both specialist model and foundation model. However, current affinity calculation merely relies on only support-query matching, without considering the query-specific semantic or the semantic correlation among inter-support samples, which limits the representation ability of affinity map. In this paper, we propose the Generalizing Semantic Mining (GSM) that focuses on exploiting generalizing semantic to improve the affinity calculation. Concretely, we first organize the affinity-based inference into three main steps to reveal the crucial role of affinity map. To address the low-data problem, Target Semantic Reusing module considers the query sample as a proxy reference and assigns it with proxy mask identifying its most generalizing semantic regions. Then, to generate the high-fidelity proxy mask, Query-specific Semantic Modeling module pinpoints the most generalizing regions through prior semantic analysis. Finally, Representative Re-weighting module explicitly modulates affinity calculation via generalization-aware weighting. Experiments on FSS benchmarks demonstrate that our GSM can serve as a plug-and-play free lunch for both specialist models and foundation models.

Dianbing Xi, Guoyuan An, Jingsen Zhu, Zhijian Liu, Yuan Liu, Ruiyuan Zhang, Jiayuan Lu, Yuchi Huo, Rui Wang

We propose PFAvatar (Pose-Fusion Avatar), a new method that reconstructs high-quality 3D avatars from Outfit of the Day (OOTD) photos, which exhibit diverse poses, occlusions, and complex backgrounds. Our method consists of two stages: (1) fine-tuning a pose-aware diffusion model from few-shot OOTD examples and (2) distilling a 3D avatar represented by a neural radiance field (NeRF). In the first stage, unlike previous methods that segment images into assets (e.g. garments, accessories) for 3D assembly, which is prone to inconsistency, we avoid decomposition and directly model the full-body appearance. By integrating a pre-trained ControlNet for pose estimation and a novel Condition Prior Preservation Loss (CPPL), our method enables end-to-end learning of fine details while mitigating language drift in few-shot training. Our method completes personalization in just 5 minutes, achieving a 48x speed-up compared to previous approaches. In the second stage, we introduce a NeRF-based avatar representation optimized by canonical SMPL-X space sampling and Multi-Resolution 3D-SDS. Compared to mesh-based representations that suffer from resolution-dependent discretization and erroneous occluded geometry, our continuous radiance field can preserve high-frequency textures (e.g., hair) and handle occlusions correctly through transmittance. Experiments demonstrate that PFAvatar outperforms state-of-the-art methods in terms of reconstruction fidelity, detail preservation, and robustness to occlusions/truncations, advancing practical 3D avatar generation from real-world OOTD albums. In addition, the reconstructed 3D avatars support downstream applications such as virtual try-on, animation, and human video reenactment, further demonstrating the versatility and practical value of our approach.

Dianbing Xi, Jiepeng Wang, Yuanzhi Liang, Xi Qiu, Yuchi Huo, Rui Wang, Chi Zhang, Xuelong Li

In this paper, we propose a novel framework for controllable video diffusion, OmniVDiff , aiming to synthesize and comprehend multiple video visual content in a single diffusion model. To achieve this, OmniVDiff treats all video visual modalities in the color space to learn a joint distribution, while employing an adaptive control strategy that dynamically adjusts the role of each visual modality during the diffusion process, either as a generation modality or a conditioning modality. Our framework supports three key capabilities: (1) Text-conditioned video generation, where all modalities are jointly synthesized from a textual prompt; (2) Video understanding, where structural modalities are predicted from rgb inputs in a coherent manner; and (3) X-conditioned video generation, where video synthesis is guided by finegrained inputs such as depth, canny and segmentation. Extensive experiments demonstrate that OmniVDiff achieves state-of-the-art performance in video generation tasks and competitive results in video understanding. Its flexibility and scalability make it well-suited for downstream applications such as video-to-video translation, modality adaptation for visual tasks, and scene reconstruction.

Yao Wu, Mingwei Xing, Yachao Zhang, Fangyong Wang, Xiaopei Zhang, Yanyun Qu

Domain generalization (DG) and domain adaptation (DA) for 3D semantic segmentation enable the model to maintain high performance while avoiding labor-intensive and time-consuming annotation of target-domain data. However, under adverse weather conditions, the injection of spatial noise will affect the reflectivity of LiDAR point clouds, exacerbate domain distribution discrepancies, and degrade the generalization ability of the model. Current methods mainly rely on sparse convolution-based architecture. Due to its limited receptive field, the model captures varying local geometric information when dealing with point clouds of different sparsities, thereby limiting its transferability. To this end, we propose BeyondSparse, a novel cross-domain 3D semantic segmentation method under adverse weather that incorporates a state-space model into a 3D sparse convolution-based architecture, sequentially modeling all features to learn domain-invariant representations. This method consists of two main components: domain feature decoupling and Mamba-based encoder. The former performs feature disentanglement before sequential modeling, while the latter performs global modeling on voxelized point cloud data. In addition, we introduce a token-style augmentation to capture the intrinsic properties of input data. Extensive experimental results demonstrate that our method outperforms SOTA competitors in both DG and DA tasks, for instance, achieving +4.6% and +0.8% mIoU on ``SynLiDAR to SemanticSTF''.

Xuexin Wu, Zhenhui Ding, Huisi Wu, Jing Qin

Recent advances in deep learning have led to significant improvements in nuclei segmentation from histological images, particularly when labels of all classes are available simultaneously during training. However, in clinical practice, real-world scenarios require a model to perform well in an incremental learning setting, where we anticipate the model to achieve satisfactory performance on previously unseen data while effectively mitigating catastrophic forgetting of old classes. Most previous methods alleviate forgetting by distilling old class knowledge through prototypes; however, they fail to adequately capture fine-grained details to address the challenge of high class similarity, which is particularly severe in histological images. To overcome these limitations, we propose a novel incremental learning method for nuclei segmentation (we call it CiNuSeg), which is composed of two key innovative modules. First, we propose a new Anchor-driven Consistency Learning (ACL) module to construct multi-level class anchors within each sample to effectively capture fine structural and textural details of nuclei, thereby significantly mitigating forgetting. Second, we develop a Dual Region Regularization (DRR) module to suppress new class representations within old class regions while enhancing new class representations within new class regions, strengthening the model's ability to discriminate between different nuclei types and improving inter-class separability. We further introduce an Adaptive Temperature Tuning (ATT) strategy to dynamically balance model stability and plasticity. Extensive experiments conducted on benchmarking MoNuSAC and CoNSeP pathological datasets demonstrate the effectiveness of our method, consistently achieving better performance than SOTAs in different settings. Codes will be available upon publication.

Lekang Wen, Jing Xiao, Liang Liao, Jiajun Chen, Mi Wang

Modality-agnostic Semantic Segmentation (MaSS) aims to achieve robust scene understanding across arbitrary combinations of input modality. Existing methods typically rely on explicit feature alignment to achieve modal homogenization, which dilutes the distinctive strengths of each modality and destroys their inherent complementarity. To achieve cooperative harmonization rather than homogenization, we propose CHARM, a novel complementary learning framework designed to implicitly align content while preserving modality-specific advantages through two components: (1) Mutual Perception Unit (MPU), enabling implicit alignment through window-based cross-modal interaction, where modalities serve as both queries and contexts for each other to discover modality-interactive correspondences; (2) A dual-path optimization strategy that decouples training into Collaborative Learning Strategy (CoL) for complementary fusion learning and Individual Enhancement Strategy (InE) for protected modality-specific optimization. Experiments across multiple datasets and backbones indicate that CHARM consistently outperform the baselines, with significant increment on the fragile modalities. This work shifts the focus from model homogenization to harmonization, enabling cross-modal complementarity for true harmony in diversity.

Changsong Wen, Zelin Peng, Yu Huang, Wei Shen

Recent advances in multimodal large language models (MLLMs) have demonstrated strong capabilities in addressing open-world segmentation tasks. However, the substantial computational cost of the LLM components presents a significant challenge, especially in segmentation tasks, where efficiency has long been a central concern. Existing efficient MLLM approaches typically reduce computation cost by pruning visual tokens in the early layers, as they account for the majority of the input sequence. Despite their efficiency, this is incompatible with dense prediction tasks such as segmentation, since removing visual tokens leads to the loss of essential object parts and spatial details. To better understand the roles of visual tokens in segmentation, we analyze the attention weights of both image and mask tokens within LLM. We find that image tokens are important throughout all layers, whereas mask tokens only attend to image tokens at deeper layers. Based on the observation, we build an efficient segmentation framework based on MLLMs by introducing a sophisticated token routing strategy. This strategy dynamically determines when and how different tokens participate in computation: For mask tokens, they are only inserted at deeper layers of the LLM to reduce redundant computation, since they rarely attend to image tokens in early layers; For image tokens, only a small number of them, named proxies, are updated via full feedforward network (FFN) computation, while the update of the remaining tokens is guided by these proxies, i.e., efficiently computed through a lightweight projector applied on the difference of the proxies during their update. Our method achieves a 1.5× acceleration over the original LLM process by reducing its FLOPs to 56%, while maintaining the same segmentation performance.

Meng Wei, Kun Yuan, Shi Li, Yue Zhou, Long Bai, Nassir Navab, Hongliang Ren, Hong Joo Lee, Tom Vercauteren, Nicolas Padoy

Enabling intuitive, language-driven interaction with surgical scenes is a critical step toward intelligent operating rooms and autonomous surgical robotic assistance. However, the task of referring segmentation, localizing surgical instruments based on natural language descriptions, remains underexplored in surgical videos, with existing approaches struggling to generalize due to reliance on static visual cues and predefined instrument names. In this work, we introduce SurgRef, a novel motion-guided framework that grounds free-form language expressions in instrument motion, capturing how tools move and interact across time, rather than what they look like. This allows models to understand and segment instruments even under occlusion, ambiguity, or unfamiliar terminology. To train and evaluate SurgRef, we present Ref-IMotion, a diverse, multi-institutional video dataset with dense spatiotemporal masks and rich motion-centric expressions. SurgRef achieves state-of-the-art accuracy and generalization across surgical procedures, setting a new benchmark for robust, language-driven surgical video segmentation.