Computer Vision
Exploration Matters for Escaping the Blur Trap in 3D Gaussian Splatting
Chengbo Wang, Guozheng Ma, Jinhong Wu et al. (+2 more)
3D Gaussian Splatting (3DGS) employs Gaussian primitives for explicit scene representation, facilitating real-time, high-fidelity reconstruction and novel view synthesis of complex scenes. However, the explicit modeling inherent in 3DGS introduces a gradient bias during optimization, rendering its non-convex optimization process highly susceptible to convergence toward local suboptimal solutions. This constitutes a fundamental limitation in 3DGS optimization, which we term the Blur Trap. To address this limitation, we integrate simple explicit exploration into the 3DGS optimization framework. First, through rigorous mathematical analysis of the 3DGS optimization formulation, we identify the underlying optimization bias responsible for the Blur Trap and categorize it into two distinct subtypes: the Far-Side Blur Trap and the Near-Side Blur Trap. Subsequently, we propose two highly straightforward exploration strategies (Random Seeding and Random Splitting) to mitigate the far-side and near-side blur traps, respectively. Experimental validation demonstrates that the incorporation of these exploration operators effectively and complementarily overcome the Blur Trap, achieving high-quality rendering performance across multiple
datasets. Project page: https://chengbo-wang.github.io/ExploreGS/
Read the full abstract ▾
All authors Chengbo Wang, Guozheng Ma, Jinhong Wu, Tie Ji, Yizhen Lao
Computer Vision
MuViSeg: Multi-View Segment Correspondences from Dense Geometry Priors
Denis Fatykhoph, Timur Akhtyamov, Konstantin Pakulev et al. (+2 more)
Object-level mapping and topological
navigation reason about whole objects, yet the correspondences they rely on are computed over keypoints or pixels and only aggregated into objects afterwards. A recent line of work removes this detour by matching directly at the level of instance segments: a class-agnostic segmenter partitions each image, and per-segment descriptors are pooled from large 3D foundation models over the masks. This shifts the open question to how frozen foundation features should be processed once the unit of matching is a segment. We introduce MuViSeg, three learned matching heads: a LightGlue-style
attention head on frozen MASt3R descriptors; a DPT-style multi-scale fusion module that exposes layered spatial detail from VGGT before pooling; and, as our main contribution, a joint multi-view head that attends over segments from several views at once, recovering transitive correspondences that pairwise matchers cannot express. In zero-shot evaluation on Replica and Virtual KITTI 2 across 0–180 degree viewpoint changes, our heads consistently improve over a parameter-free Sinkhorn matcher on the same backbone. Across 102 HM3D
navigation episodes, direct segment matchers and sparse keypoint aggregation are statistically indistinguishable, while dense matches voted into masks lose 13.7–18.0 SPL.
Read the full abstract ▾
All authors Denis Fatykhoph, Timur Akhtyamov, Konstantin Pakulev, German Devchich, Gonzalo Ferrer
Computer Vision · Cross-listed from cs.GR
Packet-Loss Robust 3D Gaussian Compression via Atomic Packaging and GNN-based Error Concealment
Yuxuan Tao, Xuerui Ma, Hao Zhang et al. (+1 more)
3D Gaussian Splatting (3DGS) and recent compression schemes such as HAC++ enable high-fidelity real-time neural rendering, but their bitstreams are fragile under packet loss during network streaming. Existing compression methods often separate correlated anchor attributes into independent streams, so losing one packet can create attribute-inconsistent broken anchors and severe rendering artifacts. We propose a packet-loss robust 3DGS transmission and error concealment framework. On the encoder side, anchor-level atomic packaging jointly encapsulates all attributes of each anchor, converting corrupted-attribute failures into clean missing-anchor erasures. Stratified random grouping further disperses packet losses across the spatial domain to avoid large contiguous voids. On the decoder side, we formulate recovery as prior-aware attribute inpainting. A Context-Aware Residual Interpolation (CARI) branch uses hash-grid prior predictions and neighboring residuals to build a robust baseline, while a lightweight two-layer graph neural network with cross-
attention over hash-grid priors refines high-frequency attribute residuals. Attribute-wise confidence control falls back to interpolation when learned predictions are unreliable. Experiments under 20 percent random packet loss on BungeeNeRF, Mip-NeRF 360, and Tanks and Temples show that the proposed method substantially improves over no-concealment transmission and limits average PSNR degradation to about 3 dB relative to the lossless HAC++ reference.
Read the full abstract ▾
All authors Yuxuan Tao, Xuerui Ma, Hao Zhang, Chunhua Peng
Computer Vision
Locality-Aware Density Control for Efficient Gaussian-based Image Representation
Jiacong Chen, Qingyu Mao, Xiandong Meng et al. (+5 more)
2D Gaussian Splatting is an attractive direction for image representation due to its explicit formulation, fast rasterization, and favorable decoding efficiency. The representation quality of this paradigm depends on the proper allocation of Gaussian capacity to the demanding regions. However, existing methods fail to allocate Gaussian capacity efficiently during optimization: under-reconstructed content is often refined in a fragmented pixel-wise manner, while neighboring optimized Gaussians with similar attributes are redundantly retained. This inefficiency motivates the need for a density control framework that jointly addresses insufficient allocation in under-reconstructed regions and redundant allocation in over-reconstructed regions. Our key insight is that this framework should exploit two complementary forms of locality: the local continuity of reconstruction errors in image space for improved Gaussian allocation, and the local similarity of neighboring Gaussians in Gaussian space for redundant elimination. Based on this insight, we propose Locality-Aware Density Control (LocoADC), a plug-and-play framework that improves Gaussian capacity utilization through Region-wise Gaussian Densification (RGD) and Similarity-Driven Gaussian Merging (SDGM) strategies, together with a local color consistency constraint for more reliable merging. Extensive experiments on diverse
datasets show that LocoADC consistently improves multiple baselines by enabling more effective local Gaussian allocation, including a 2.93 dB PSNR gain over GI on the CLIC
dataset under the same 30k Gaussian budget. Code is available at: https://github.com/ChenJiaCong-1005/LocoADC.
Read the full abstract ▾
All authors Jiacong Chen, Qingyu Mao, Xiandong Meng, Shuai Liu, Chao Li, Fanyang Meng, Youneng Bao, Yongsheng Liang
Computer Vision
Leveraging Dissimilarity Invariance as a Robust Anchor for Learning with Noisy Labels
Wenxiao Fan and Kan Li
Deep learning models excel in visual recognition but suffer severe performance drops when training labels are corrupted by noise. Under label noise prior work cannot learn accurate similarities and thus misguide the learning process. In this paper, we uncover a complementary and novel phenomenon, Dissimilarity Invariance, whereby semantic dissimilarity between unrelated samples remains stable despite label noise. Leveraging this insight, we propose NegScale, a plug-and-play framework that shifts focus from fragile similarity to robust dissimilarity. NegScale integrates: (1) Structured Negative Orthogonality Penalty (SNOP), enforcing subspace orthogonality for unrelated samples; and (2) Dissimilarity-Calibrated Similarity Adjustment (DCSA), suppressing spurious similarity using dissimilarity anchors. We also give theoretical analysis that proves Dissimilarity Invariance and the effectiveness of NegScale. Empirical results demonstrate that NegScale consistently outperforms state-of-the-art baselines, establishing new
benchmarks on CIFAR with synthetic noise and real-world
datasets.
Read the full abstract ▾
Computer Vision · Cross-listed from cs.HC
AlphaOracle: Oracle bone script decipherment via human-workflow-inspired deep learning
Yuliang Liu, Haisu Guan, Pengjie Wang et al. (+11 more)
Approximately 3,000 of the 4,500 oracle bone script (OBS) characters remain undeciphered due to fragmentary inscriptions and sparse evidence. Current AI approaches fail to replicate expert workflows that integrate form analysis, contextual semantics, and philological
reasoning. We introduce AlphaOracle, a human-workflow-inspired framework that systematizes OBS decipherment using the largest digitized corpus to date. Its multi-stage pipeline comprises: (i) rubbing parsing; (ii) radical-based morphological analysis with diachronic modeling; (iii) contextual
retrieval with semantic
alignment; and (iv) philological validation against classical sources. Each stage generates explicit, confidence-weighted evidence chains, culminating in interpretable reports for scholarly verification. Across multiple test characters, AlphaOracle's readings strongly agreed with expert interpretations. In a study of 86 domain specialists, it reduced analysis time by 64% and 79% of participants rated it highly useful. Notably, AlphaOracle resolves the character "Lao" as a toponymic or clan designation, offering concrete revisions to Shang administrative and social interpretations. These results suggest that computational methods aligned with philological practice can facilitate OBS research and provide a conceptual reference for studies of other undeciphered scripts.
Read the full abstract ▾
All authors Yuliang Liu, Haisu Guan, Pengjie Wang, Xinyu Wang, Jinpeng Wan, Kaile Zhang, Handong Zheng, Xingchen Liu, Zhebin Kuang, Huanxin Yang, Bang Li, Yongge Liu, Lianwen Jin, Xiang Bai
Computer Vision
CaT-GS: Efficient 3DGS Rendering for Large Scale Scenes via Inter-frame Caching and Tile Scheduling
Tingjia Zhang, Bo Chen, Shengzhong Liu et al. (+2 more)
Recent breakthroughs in 3D Gaussian Splatting (3DGS) have advanced neural rendering with high fidelity and speed. However, its performance degrades significantly in large-scale scenes due to the computational burden of tile-based rasterization. Existing optimization efforts either require costly scene re-training or focus on narrow aspects of the pipeline, overlooking critical inefficiencies in real-world deployments. Through a comprehensive analysis, we identify three primary sources of redundancy and low GPU utilization: redundant inter-frame pre-processing, viewpoint-based occlusion redundancy, and severe tile-level load imbalance. To address these issues, we propose CaT-GS, a novel and efficient 3DGS rendering pipeline. CaT-GS introduces a speculative multi-frame preprocessing method to eliminate redundant computations across consecutive frames, and an inter-frame caching mechanism to eliminate viewpoint redundant rendering stages. Furthermore, it refactors rasterization tasks with a dedicated kernel to mitigate tile load imbalance, significantly boosting GPU utilization. Extensive experiments demonstrate that CaT-GS achieves a speedup of up to 10 times over the original 3DGS and up to 70% over previous state-of-the-art methods, establishing a new
benchmark for high-fidelity, real-time rendering of large-scale scenes.
Read the full abstract ▾
All authors Tingjia Zhang, Bo Chen, Shengzhong Liu, Fan Wu, Guihai Chen
Computer Vision
Measuring and Improving Complex-Atomic Answer Consistency in Endoscopic VQA
Yuhao Liu, Cheng Zhao and Guanghui Yue
Endoscopic visual question answering (VQA) increasingly asks complex questions that combine several endoscopic answer components rather than isolated factual queries. Such complex answers may be scored as correct even when the same model fails on associated atomic questions. We introduce EndoCA, a paired complex-atomic answer consistency
benchmark for evaluating whether complex answers remain consistent with same-image atomic answers. EndoCA contains two suites: EndoCA-Core evaluates compact question-complexity patterns commonly seen in practical endoscopic VQA, and EndoCA-Diagnostic supports controlled analysis across increasing question complexity. We evaluate 11 VLMs spanning open, medical, endoscopy-adapted, and closed-source models on EndoCA. Some VLMs achieve high complex-answer accuracy, yet their atomic-answer accuracy and complex-atomic answer consistency remain substantially lower. To reduce this complex-atomic inconsistency, we introduce Atomic-Support Reconciliation (ASR), a training-free mechanism that uses model-generated atomic answers as contextual premises for answer revision and consistency-guided selective answering. On four selected publicly available models, ASR-Revise improves paired complex-atomic correctness with modest changes in complex-answer accuracy, while ASR-Selective improves accuracy on answered cases by allowing the model to abstain from less reliable cases. Together, EndoCA and ASR provide a consistency-aware
benchmark and a training-free mechanism for answer reconciliation and selective answering in endoscopic VQA.
Read the full abstract ▾
Computer Vision
Consistent Feature Transport for Image Relighting
Bohan Zhang, Huanwei Liang, Yuhan He et al. (+5 more)
Image relighting modifies illumination while preserving non-lighting content such as identity and geometry. Existing
diffusion-based methods often suffer from unstable illumination changes or inconsistent content preservation under complex lighting, as they lack an explicit mechanism to learn feature transformations between images. We reformulate relighting as an illumination feature transport problem and introduce Consistent Feature Transport (CFT), a training principle that explicitly enforces illumination-consistent transport between source and target image distributions. Built upon rectified flow, CFT jointly models noise-to-image generation and illumination-consistent source-to-target transport through trajectory-level supervision. This dual-transport formulation encourages isolation of illumination-specific variations while preserving content-aligned features. To support complex lighting scenarios, we construct a large-scale portrait relighting
dataset with diverse relighting effects. Experiments show consistent improvements over existing state-of-the-art relighting approaches and demonstrate that CFT can generalize to other editing tasks, including style transfer. Code is available at https://github.com/Dixin-Lab/CFT.
Read the full abstract ▾
All authors Bohan Zhang, Huanwei Liang, Yuhan He, Hongteng Xu, Quxiao Chao, Luoqi Liu, Dixin Luo, Ting Liu
Computer Vision
PRiSM: Prototype Regularization for Few-Shot VLMs
Ghassen Baklouti, Omprakash Chakraborty, Jose Dolz et al. (+1 more)
Training-free few-shot adaptation methods have gained significant
attention recently in the context of
Vision-
language Models (VLMs). Yet, current
benchmarks rely on strong assumptions about the statistics of the adaptation data, e.g., class balance. We question these simplifying assumptions and introduce a more realistic
benchmark that varies both the levels of class balance and the effective number of classes in few-shot tasks via Dirichlet sampling. Surprisingly, under our setting, we observe substantial drops in the performances of state-of-the-art methods, more so when the number of labeled samples increases. To mitigate this, we introduce PRiSM, a class-prototype regularization that can be deployed as a plug and play module on top of any existing baseline method, significantly improving performances. Our method optimizes a novel multi-term loss, which includes a regularizer maximizing inter-class pairwise distances, along with additional terms promoting support-feature
alignment and fidelity to the baseline prototypes. Furthermore, we introduce an effective and computationally efficient block Majorize-Minimize optimizer for our objective. More specifically, we derive a valid blockwise Lipschitz constant (i.e., a bound on the Hessian's spectral norm), which can be computed efficiently via the Gershgorin circle
theorem. Extensive experiments show that PRiSM improves several training-free baselines, with large gains when dealing with severe class imbalance and high numbers of classes.
Read the full abstract ▾
All authors Ghassen Baklouti, Omprakash Chakraborty, Jose Dolz, Ismail Ben Ayed
Computer Vision
Vis2Reg: Visibility-Aware Landmark-Free Geometric 3D–2D Registration for Liver Laparoscopy
Jiaming Feng, Xukun Zhang, Shahid Farid et al. (+1 more)
Accurate 3D–2D liver registration, which aligns preoperative 3D models to partial, view-dependent intraoperative surface observations, is critical for AR-guided laparoscopic surgery but remains challenging due to severe occlusion, limited visibility, and the lack of 3D ground-truth supervision. Existing landmark-free approaches perform partial-to-complete
geometric alignment, yet robust self-supervision under extreme partial visibility remains difficult. We propose Vis2Reg, a visibility-aware registration framework that explicitly constrains deformation using mask-consistent visible regions. We introduce a visibility-aware self-supervision that derives a visible-domain 3D supervision signal from intraoperative masks, enabled by differentiable point rasterization and mask-guided back-projection. This formulation improves robustness under severe occlusion while maintaining fully self-supervised learning. Vis2Reg combines a robust
geometric rigid initialization module with an implicit neural deformation field for stable
alignment. Vis2Reg achieves a Dice score of 92.6% and a Chamfer Distance of 1.43 mm on real intraoperative
datasets, with 111 ms per-frame inference time, demonstrating both accuracy and practical efficiency.
Read the full abstract ▾
All authors Jiaming Feng, Xukun Zhang, Shahid Farid, Sharib Ali
Computer Vision
FF-ProCams: Feed-Forward Gaussian Splatting for Projector-Camera System
Ziyao Wang, Yuqi Li, Wenxing Zheng et al. (+2 more)
Projector-camera (ProCams) systems achieve active scene perception and controllable appearance manipulation via structured illumination, serving as a core infrastructure for spatial augmented reality, projection mapping, and surface reflectance acquisition. Existing inverse-rendering methods for ProCams deliver high-fidelity results but rely on time-consuming per-scene optimization, while mainstream feed-forward 3D reconstruction models produce baked appearance that cannot adapt to spatially varying projector illumination. To resolve this accuracy-efficiency trade-off, we propose FF-ProCams, a Feed-Forward 3D Gaussian inverse-rendering framework for ProCams. A hybrid Mamba2-
Transformer encoder aggregates cross-view
geometric and photometric cues from sparse multi-view observations, and lightweight heads predict a relightable Gaussian representation in a single forward pass. We further design a projector-aware differentiable renderer to synthesize camera observations under arbitrary active illumination and ProCams poses. To enable feed-forward training, we construct a large-scale synthetic ProCams
dataset covering diverse object geometries and surface materials. Experiments show FF-ProCams achieves high-fidelity projector-aware rendering, generalizes to unseen patterns, and supports novel projector-camera poses. Using only 8 input views, it outperforms optimization-based baselines with 297 views while reducing test-time reconstruction to 0.13 seconds (a three-to-five-order-of-magnitude speedup). The code and data are available at https://github.com/CPREgroup/FF-ProCams/.
Read the full abstract ▾
All authors Ziyao Wang, Yuqi Li, Wenxing Zheng, Jiaying Chen, Chong Wang
Computer Vision
Toward Optimal Adenovirus Detection Using YOLO26
Olivier Rukundo
This study systematically
benchmarks different data augmentation setups across the baseline YOLO26 model size variants to determine the most effective setup for adenovirus detection in TEM images. The benchmarked setups include NAS, GAS, GMAS, and DAS, all evaluated under identical training conditions. A modified YOLO26 model leveraging P2, expanded STAL, increased topk, and MuSGD was also tested across the same benchmarked setups. The adenovirus
dataset, selected from the published TEM virus
dataset, was re-annotated by leveraging adenovirus particle positions to generate YOLO-compatible bounding box annotations. The modifications produced their largest performance gains under GAS and GMAS, with modified YOLO26x trained using GAS achieving a mAP@50 of 0.80, Precision of 0.81 and a Recall of 0.80
Read the full abstract ▾
Computer Vision
ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video
Xiaozhong Lyu, Gen Li, Zhiyin Qian et al. (+3 more)
Egocentric devices, such as wearable front-facing cameras, provide a unique perspective for capturing the continuous interaction between a human viewer and the surrounding environment. A holistic and efficient
multimodal model capable of reconstructing this 4D representation is therefore highly desirable. However, existing approaches often rely on auxiliary inputs such as pre-computed camera trajectories, treat scene perception and human ego-motion modeling as separate problems despite their strong interdependency, and suffer from slow inference time. To address these limitations, we present ReViV, the first unified framework for holistic
egocentric 4D reconstruction that extracts both viewer and view dynamics from a single
monocular RGB
video. We formulate the task as learning the full joint probability distribution over
multimodal signals, including RGB
video, camera trajectory, gaze direction, full-body motion, hand motion, and depth. Powered by a Masked Generative
Egocentric Transformer, ReViV operates within a single feed-forward architecture to simultaneously reconstruct the temporally consistent 4D reconstruction across the viewer and the view with fast inference speed. Extensive experiments on diverse
benchmarks, including HoloAssist, HOT3D, ARCTIC, Aria Digital Twin, and TACO, demonstrate that ReViV achieves state-of-the-art accuracy and efficiency across holistic ego-body, hand, and gaze reconstruction, camera tracking, while maintaining highly competitive
egocentric depth estimation without relying on heavy task-specific priors. Code and models are fully open-sourced: https://reviv4d.github.io/.
Read the full abstract ▾
All authors Xiaozhong Lyu, Gen Li, Zhiyin Qian, Xucong Zhang, Marc Pollefeys, Siyu Tang
Computer Vision
Medical Imaging Fusing Vision Transformer: Laryngeal Cancer Screening with Explanation
Haiyang Wang and Luca Mainardi
Early and timely screening of laryngeal cancer is crucial for improving clinical outcomes. In recent years, NBI endoscopy has become a standard diagnostic tool for the detection of laryngeal lesions. However, its effective use requires well-trained clinicians and the procedure is time-consuming and subject to interobserver variability. In this context, the application of artificial intelligence (AI) offers a promising solution to support clinical decision-making. In this work, we proposed applying
transformer and
attention mechanism for analyzing the narrow band imaging and distinguish benign and malignant lesions. Results show it has good classification performance with F1 (82.72%), accuracy(82.33%). In addition, the result of laryngeal cancer screening is explainable for clinicians. The explainability is utilizing the state of art
segmentation method (MedSAM) to provide the useful pathological information area for clinicians. The proposed methodology fusing classification and
segmentation provides a translating on laryngeal cancer screening.
Read the full abstract ▾
Computer Vision
BrainNext: A General-Purpose Self-Supervised Foundation Model for Brain MRI Analysis
Moona Mazher, Abdul Qayyum, Steven A. Niederer et al. (+1 more)
Foundation models pretrained using self-supervised learning have transformed computer
vision by learning transferable representations from large-scale unlabeled data. However, existing foundation models for neuroimaging remain limited by task-specific training, slice-based learning strategies, or relatively small pretraining
datasets, restricting their generalizability across diverse
brain MRI applications. In this work, we present BrainNext, a general-purpose self-supervised foundation model for volumetric
brain MRI analysis. BrainNext combines masked autoencoder (MAE) pretraining with a native three-dimensional Bi-Directional xLSTM-UNet architecture to learn rich anatomical representations from 60,551 unlabeled
brain MRI examinations spanning multiple MRI modalities. The pretrained model is subsequently adapted to downstream tasks through lightweight task-specific fine-tuning. We evaluate BrainNext on the Foundation Models for Medical Imaging (FOMO) 2025 Method Track, encompassing classification,
segmentation, and
brain-age estimation, where it achieved second place overall and ranked first in the meningioma
segmentation task on the official FOMO 2025 challenge leaderboard, demonstrating strong transferability across heterogeneous neuroimaging tasks. These results highlight the potential of large-scale self-supervised pretraining to learn robust and transferable volumetric representations, establishing BrainNext as a scalable foundation model for diverse
brain MRI applications.
Read the full abstract ▾
All authors Moona Mazher, Abdul Qayyum, Steven A. Niederer, Daniel C. Alexander
Computer Vision
CDIS: Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging
Juno Kim, Hye-Jung Yoon, Yesol Park et al. (+1 more)
Class-agnostic 3D instance
segmentation is critical for robotic systems operating in unknown environments, enabling perception of previously unseen objects for reliable manipulation and
navigation. Existing approaches typically project per-frame 2D instance masks into 3D and merge them, which often breaks object identities across time and yields fragmented 3D instances. We introduce Cross-Dimensional Class-Agnostic 3D Instance
Segmentation (CDIS), a zero-shot framework that explicitly tracks 2D instance masks across frames and associates them with 3D superpoints, creating a feedback loop between 2D and 3D. This cross-dimensional
reasoning links temporally stable 2D tracks with spatially coherent 3D regions, producing globally consistent 3D instance labels without any 3D-specific training. Experiments on
benchmark datasets demonstrate that CDIS achieves higher accuracy and consistency than state-of-the-art zero-shot methods, while remaining efficient and scalable to diverse real-world environments.
Read the full abstract ▾
All authors Juno Kim, Hye-Jung Yoon, Yesol Park, Byoung-Tak Zhang
Computer Vision
Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence
Katarzyna Filus and Sebastian Pokuciński
Within Explainable Artificial Intelligence, mechanistic interpretability uses Sparse Autoencoders (SAEs) to extract more interpretable features from neural representations. However, assessing their monosemanticity, and thus explanation quality, remains challenging. Existing metrics require external concept labels or depend on pretrained
embedding models, making them sensitive to encoder's geometry. We introduce the Tversky Monosemanticity Score (TMS), a label-free metric that operationalizes monosemanticity as activation-set coherence of binarized SAE latents, and does not require external
embedding encoders. We evaluate TMS on SAEs trained on features from pretrained
vision and
vision-
language models (DINOv3, CLIP, BLIP2), two common SAE regimes (TopK, BatchTopK), multiple sparsity levels, and expansion factors. Our results show that TMS is less affected by encoder anisotropy than its
embedding-based alternative, while remaining aligned with established monosemanticity indicators. TMS also reveals distinct SAE training dynamics across base models. Moreover, under encoder anisotropy, TMS provides a stronger indication of probe-based concept deletion effectiveness, while being competitive otherwise.
Read the full abstract ▾
Computer Vision · Cross-listed from cs.RO
From Sign Language Generation to Humanoid Execution: Vision-Language Guided Retargeting with Collision Mitigation
Nabeela Khan, Bowen Wu, Runwu Shi et al. (+5 more)
Recent sign
language generation (SLG) systems increasingly output dense 3D body representations, which better preserve full-body kinematics and geometry for downstream embodiment on
humanoid robots. However, these generated motions frequently exhibit self-intersections such as hand-hand and hand-torso penetration. While such artifacts may be tolerated in offline rendering, they become critical in
humanoid execution as they lead to infeasible inverse-kinematics (IK) solutions, collisions, and unstable retargeted trajectories. We present a system-level framework that bridges SLG outputs to
humanoid joint-space execution via two components. First, we introduce a volumetric SMPL-X collision-mitigation module that projects generated signing motions toward physically plausible configurations while minimally deviating from the original trajectory. Second, we propose a
vision-
language-guided retargeting
algorithm built on an IK backbone: a VLM serves as a visual critic over rendered
humanoid motion, identifies embodiment-specific failure modes, and triggers targeted task-space corrections. Our results highlight collision handling and perception-guided refinement as key missing components for reliable
humanoid signing.
Read the full abstract ▾
All authors Nabeela Khan, Bowen Wu, Runwu Shi, Benjamin Yen, Takeshi Ashizawa, Carlos Toshinori Ishi, Takashi Minato, Kazuhiro Nakadai
Computer Vision
To Blend In, First Decouple: Rethinking Camouflage Image Generation via Context-Decoupled Representations
Wenzhuang Wang, Yifan Zhao, Mingcan Ma et al. (+4 more)
Camouflage image generation (CIG) focuses on generating visually concealed objects that seamlessly blend into their backgrounds. Existing methods typically follow either background-guided paradigms that adapt object appearance via style transfer, or foreground-guided strategies that outpaint surrounding regions conditioned on object features. However, they still suffer from appearance discrepancy and background artifacts. We attribute these limitations to cross-context representation leakage, where object and background cues are entangled in a coupled conditional space, resulting in ambiguous control and degraded camouflage fidelity. To tackle this, we propose a new context-decoupled generative paradigm, termed CamoDreamer, which aims to isolate contextual conditional guidance and explicitly decouple latent camouflage features into coordinated object and background control streams. First, a Contrast-aware Contextual Bridge is designed to model cross-context discrepancies and construct contrast-aware dual conditional guidance. Second, Context-Decoupled Assimilation Streams are employed to separate generative interactions conditioned on the dual guidance, while facilitating background rendering with target-aware cues in the latent space. Finally, a Frequency-Adaptive Contextual Blend module integrates complementary high-frequency textures and low-frequency structures from decoupled features to improve holistic coherence. Extensive experiments demonstrate that CamoDreamer consistently outperforms existing methods with a substantial margin, while maintaining a relatively lightweight design.
Read the full abstract ▾
All authors Wenzhuang Wang, Yifan Zhao, Mingcan Ma, Yunlong Che, Haoran Chen, Ming Liu, Jia Li
Computer Vision
DA-Fusion: Deformable Attention-Based RGB-D Fusion Transformer for Unseen Object Instance Segmentation
Yesol Park, Hye-Jung Yoon, Juno Kim et al. (+1 more)
In logistics automation, precise
segmentation of unseen objects is crucial for efficient robotic manipulation in cluttered environments. Tasks such as bin-picking and shelf-picking require robust perception to handle occlusions, varying object shapes, and complex spatial arrangements. Traditional RGB-based methods tend to over-segment objects due to their reliance on texture, while depth-based methods often under-segment by focusing primarily on
geometric features. To address these limitations, we propose DA-Fusion, a deformable
attention-based RGB-D fusion
Transformer designed for unseen object instance
segmentation. DA-Fusion effectively combines the strengths of both RGB and depth data, enhancing
segmentation accuracy in cluttered and multi-layered object environments. We also introduce the Object Clutter Bin
Dataset (OCBD), a
benchmark dataset specifically tailored for evaluating bin-picking scenarios in top-down views. Extensive evaluations demonstrate that DA-Fusion outperforms state-of-the-art methods across diverse environments, making it particularly suited for real-world logistics tasks.
Read the full abstract ▾
All authors Yesol Park, Hye-Jung Yoon, Juno Kim, Byoung-Tak Zhang
Computer Vision
PC-Seg: Progressive Cross-View Consistency for 3D OCT Segmentation from Sparse 2D Annotations
Tsubasa Konno, Takahiro Ninomiya, Yukun Zhou et al. (+6 more)
Volumetric
segmentation of optical coherence
tomography (OCT) images is essential for diagnosing ocular diseases but requires labor-intensive voxel-wise annotations. While semi-supervised learning (SSL) can reduce annotation costs, most existing methods process data slice by slice and fail to exploit the inherent 3D spatial context. We propose PC-Seg, a progressive cross-view consistency framework that learns high-accuracy 3D
segmentation models from sparse 2D annotations. Unlike conventional multi-view approaches, PC-Seg uses a single 2D model to learn cross-view consistency from standard B-scans and orthogonal slices, thereby generating reliable volumetric pseudo-labels. These pseudo-labels are then distilled into a 3D model, followed by a co-training stage in which the 2D and 3D models mutually refine each other through ensemble pseudo-labeling. Experiments on the MSHC and Duke DME
datasets demonstrate that PC-Seg achieves accuracy comparable to fully supervised learning while using labels for only about 0.7% of the training data, outperforming state-of-the-art semi-supervised and retinal layer
segmentation methods. Our code is publicly available at https://github.com/gsisaoki/pc-seg-official.
Read the full abstract ▾
All authors Tsubasa Konno, Takahiro Ninomiya, Yukun Zhou, Koichi Ito, Siegfried K. Wagner, Yiqun Lin, Pearse A. Keane, Toru Nakazawa, Takafumi Aoki
Computer Vision · Cross-listed from cs.RO
SLAM in Low-Light Environments: Project Report
Oleh Basystyi, Anna Stasyshyn, Oleksandr Kosovan et al. (+1 more)
Simultaneous localization and mapping (SLAM) is one of the fundamental problems in robotics, as it enables autonomous operations in real-world scenarios. Under low illumination, reduced contrast, sensor noise, and motion blur degrade both feature extraction and feature matching, while compensating with
LiDAR, depth, or thermal sensors raises cost, power draw, and integration complexity. Existing
benchmarks remain dominated by well-lit indoor or daylight sequences, leaving open how far SLAM with standard RGB cameras can be pushed in the dark. We
benchmark six systems spanning the feature-based, direct, filter-based, and learning-based paradigms - ORB-SLAM3, DSO, Kimera-VIO, OpenVINS, DPVO, and DPV-SLAM - on five LaMARia sequences of varying difficulty and illumination, reporting absolute and relative pose error alongside control-point recall. Kimera-VIO is the only system to track all five sequences to completion, combining the lowest relative pose error with steadily growing absolute error due to the absence of loop closure; DPVO and DPV-SLAM never lose tracking but incur absolute errors of roughly 100 m under low light; and the classical
monocular pipelines (ORB-SLAM3, DSO) together with the filter-based OpenVINS fail outright or diverge on most of the harder and low-light sequences. The results suggest that RGB-only SLAM maintains stable low-light tracking only when both inertial fusion and global optimization are present. Closing the remaining gap will likely require low-light-specific learned front-ends or a return to complementary sensing.
Read the full abstract ▾
All authors Oleh Basystyi, Anna Stasyshyn, Oleksandr Kosovan, Yaroslav Prytula
Computer Vision
Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentation
Lingrui Li, Nan Pu, Dong Zhao et al. (+4 more)
Test-time adaptation (TTA) aims to mitigate distribution shifts by adapting models with unlabeled target data at inference time. While TTA with
vision-
language models (VLMs) has shown promising results in classification, extending it to medical image
segmentation remains challenging. In this setting, the adaptation gains from optimizing on VLM-generated predictions are often outweighed by the degradation to the VLM's strong pretrained features caused by noisy, update-driven learning, resulting in limited and unstable improvements. We therefore propose
Memory-Supported Synergistic Adaptation (MSSA), a novel training-free TTA framework for medical image
segmentation. Without updating model parameters, MSSA dynamically selects reliable image-text predictions to construct an online
memory, uses them as text-guided semantic priors, and couples them with cross-image structural
alignment for robust adaptation. Specifically, MSSA consists of (i) a noise-aware
memory construction module that filters and stabilizes cross-modal predictions, and (ii) a relevance-driven prototype
alignment module that aligns the target sample with structurally consistent
memory samples and their reliable predictions to improve adaptation. Extensive experiments on multiple medical
segmentation benchmarks demonstrate that MSSA consistently improves VLM-based
segmentation models and outperforms existing fine-tuning-based TTA methods by a clear margin, with gains of up to 12.2% DSC and 11.7% mIoU. Project page: https://lingrayy.github.io/MSSA/ .
Read the full abstract ▾
All authors Lingrui Li, Nan Pu, Dong Zhao, Wenjing Li, Andrew P French, Zhun Zhong, Xin Chen
Computer Vision · Cross-listed from eess.IV
Luminosity-Adaptive Contrast Enhancement Using CLAHE for Retinal Fundus Images with Quantitative Validation and Comparative Analysis
K. Mithra and Prem Kumar Santhanam
Background: Retinal fundus imaging is central to the early diagnosis of sight-threatening conditions including diabetic retinopathy, glaucoma, and retinal vein occlusion. Clinical utility of fundus images is routinely compromised by non-uniform illumination, motion blur, and low contrast - artefacts that increase the risk of diagnostic error. Effective image enhancement is therefore a prerequisite for reliable computer-aided ophthalmic diagnosis. Methods: This study proposes a two-stage image enhancement pipeline combining luminosity correction via HSV colour space decomposition with Contrast Limited Adaptive Histogram Equalization (CLAHE) applied exclusively to the Value (V) channel. Experiments are conducted on the publicly available DRIVE
dataset (40 retinal fundus images, 584 x 565 pixels, Canon CR5 camera, ophthalmologist-annotated ground truth). Quantitative evaluation employs Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Contrast-to-Noise Ratio (CNR). Baseline comparisons include standard Histogram Equalization (HE) and Adaptive Histogram Equalization (AHE). A binary masking step is subsequently applied to isolate hyper-reflective regions consistent with vascular pathology. Results: The proposed method achieves PSNR = 29.3 dB, SSIM = 0.91, and CNR = 3.12 - outperforming HE (PSNR = 21.4 dB, SSIM = 0.74) and AHE (PSNR = 23.1 dB, SSIM = 0.79) across all metrics, with an average processing time of 0.14 seconds per image. Conclusions: The combined luminosity-CLAHE pipeline yields measurably superior contrast and structural fidelity compared to established baseline methods, with processing speed compatible with clinical screening workflows. Limitations and directions for deep-learning-based comparison are discussed.
Read the full abstract ▾
Computer Vision
ShotPlan: Cinematic Video Generation with Learnable Planning Token
Su Guo, Guangce Liu, Haosen Yang et al. (+7 more)
Current
video generation models achieve impressive results in single-shot generation, yet remain limited in cinematic
video generation, where coherent narratives and effective multi-shot composition require explicit shot planning. To address this challenge, we propose ShotPlan, a framework for explicit multi-shot cinematic
video generation built upon a
video diffusion foundation model. Our method introduces learnable planning
tokens that capture shot-level transition cues and can be seamlessly integrated with the original
video generation
tokens to control transition timestamps. Unlike standard
video generation
tokens, the proposed planning
tokens are equipped with Fractional Temporal Rotary Position
Embedding (FRoPE), enabling shot transitions to be modeled at the frame level. Experiments demonstrate that ShotPlan significantly outperforms existing cinematic
video generation methods, offering more flexible shot management and stronger inter-shot consistency.
Read the full abstract ▾
All authors Su Guo, Guangce Liu, Haosen Yang, Jiepeng Wang, Cong Liu, Junqi Liu, Haibin Huang, Hongxun Yao, Chi Zhang, Xuelong Li
Computer Vision
Attention from Above: A Multimodal Model for Drone-Based Object Localization
Hyun-Ki Jung
Drone-based object detection technology has advanced rapidly, becoming increasingly sophisticated and efficient. Recently, research trends have expanded beyond the detection of predefined objects toward the identification of specified target objects. For example, desired targets can be specified through textual
prompts, enabling accurate detection of objects of interest. To address this demand, this paper proposes an efficient
multimodal-based object detection model aimed at improving small object detection performance. The proposed method is built upon the YOLO-World framework and replaces the C2f layers used in the YOLOv8 backbone with
attention-based A2C2f layers. This modification enables more precise representation of local features, particularly for small objects or objects with well-defined boundaries. In addition, the incorporation of
attention mechanisms and parallel processing structures significantly enhances the model's computational accuracy. Comparative experiments conducted on the VisDrone
dataset demonstrate that the proposed model outperforms the original YOLO-World model. Specifically, precision increases from 43.0% to 45.1%, recall from 32.8% to 35.0%, the F1 score from 37.2% to 39.4%, mAP@0.5 from 32.5% to 35.2%, and mAP@0.5-0.95 from 18.5% to 19.9%, confirming a substantial improvement in detection accuracy. These results verify that the proposed approach provides an effective and highly accurate solution for object detection in drone-based image and
video application environments.
Read the full abstract ▾
Computer Vision
Early Yield Prediction for Sugar Beet Fields using Satellite Data – Learnings from Specialized Vision Transformers
Philipp Vaeth, Bhumika Laxman Sadbhave, Denise Dejon et al. (+2 more)
Remote sensing has become an increasingly valuable tool for agricultural monitoring, particularly through the use of publicly available satellite imagery. However, effectively integrating domain knowledge into machine learning methods remains challenging. This study presents a real-world example of early sugar beet harvest yield
forecasting from purely optical Sentinel-2 imagery, demonstrating how a tight integration of domain knowledge and machine learning can lead to synergistic gains. We empirically find that using very small
vision transformer patch sizes and all available Sentinel-2 spectral bands improves our model despite being uncommon design choices in the domain. As a practical contribution, we were able to identify a large fraction of low-yield fields in a different year early on in the growth cycle through a modified training setup and a ranking-based detection of underperforming fields.
Read the full abstract ▾
All authors Philipp Vaeth, Bhumika Laxman Sadbhave, Denise Dejon, Gunther Schorcht, Magda Gregorova
Computer Vision
RayOcc: Occlusion-Aware Ray Occupancy Estimation via Gaussian Mixture Intensity
Junho Kim and Seongwon Lee
Camera-only 3D semantic occupancy prediction aims to infer voxel-wise scene semantics from multi-view images, yet remains fundamentally challenging due to depth ambiguity and occlusion. Along a single camera ray, multiple spatially separated surfaces may coexist, making occupancy inherently a multi-label existence problem rather than a single-depth estimation task. However, most existing approaches favor a single dominant depth hypothesis per ray, limiting their ability to model volumetric scenes under complex occlusion. To address this limitation, we introduce RayOcc, an occlusion-aware ray occupancy framework that reformulates ray modeling as multi-label existence prediction. Instead of predicting a categorical depth distribution, RayOcc estimates a non-normalized Gaussian mixture intensity along each ray and converts it into interval-wise occupancy probabilities via a Poisson event formulation, allowing multiple occupied hypotheses to coexist without enforcing mutual competition across depth. The predicted mixture components are interpreted as occupancy hypotheses to initialize sparse 3D Gaussian primitives, which are refined and rasterized for semantic occupancy prediction. Experiments on the nuScenes
benchmark show that RayOcc achieves state-of-the-art overall IoU and mIoU among the compared Gaussian-based occupancy methods.
Read the full abstract ▾
Computer Vision · Cross-listed from cs.AI
OrientSAM: Mitigating Camera-Centric Shortcut in Multimodal Spatial Reasoning via Orientation-Aware Spatial Alignment
Wenxiao Fan, Hang Yin and Kan Li
Multimodal large
language models (MLLMs) still struggle with spatial
reasoning that requires perspective transformation. In particular, they often rely on camera-centric cues rather than
reasoning from the reference object's viewpoint, leading to systematic errors in non-camera reference settings. In this paper, we first analyze this failure mode and show that object orientation is a key factor underlying such camera-centric shortcut behavior. To address this issue, we propose OrientSAM, an orientation-aware spatial
alignment framework for
multimodal models. OrientSAM injects explicit orientation information into
multimodal representations through orientation-aware
tokens and
Fourier-based angle encoding, and further adopts a curriculum learning strategy to progressively improve perspective-aware
reasoning. In addition, we build a spatial data construction pipeline to generate orientation-aware spatial supervision from large-scale images. Experiments on Spatial-MM, ViewSpatial, and 3DSRBench show that OrientSAM consistently outperforms strong baselines, especially on non-camera-view, person-centric, and orientation-sensitive tasks. The results further demonstrate that explicit orientation modeling is important for mitigating camera-centric shortcut behavior and enabling more robust allocentric spatial
reasoning in
multimodal models.
Read the full abstract ▾