cs.AI · cs.CL · cs.LG · cs.CV · cs.CR · cs.SE · stat.ML · q-fin.TR · q-fin.ST · econ.GN · q-bio.QM · physics.soc-ph · math.OC · cs.RO · cs.HC
Qiwen Gu, Xin Zhou, Xiwu Chen, Zhongyang Zhu, Zhuo Zhang and others · 2026-10-22
Controllable 3D part generation is pivotal for digital asset creation, yet existing methods lack the flexibility to accommodate diverse user workflows requiring varying levels of control. In this paper, we introduce FlexPart, a unified image-to-3D part generation framework that s…
Yunfei Xie, Howard H. Qian, Shiyi Lan, Kaiyu Hang, Chen Wei · 2026-10-22
Robotic foundation models are typically evaluated through costly closed-loop rollouts, which motivates cheap offline proxies for model capability. The Platonic Representation Hypothesis (PRH) suggests that as representations improve, different modalities such as vision and langua…
Shengqiong Wu, Meng Luo, Bobo Li, Ziwei Liu, Shuicheng Yan and others · 2026-10-22
Video foundation models have advanced rapidly in understanding and generating visual sequences, while video world models seek to capture the underlying dynamics of the world they depict. Despite their different objectives, both concern the relationship between video observations …
Sy-Tuyen Ho, Anirudh Satheesh, Soham Chawathe, Huy Nghiem, Yongkyun Lee and others · 2026-10-22
Auditing whether a text-to-image (T2I) model was fine-tuned on a particular image collection is difficult: a model can absorb collection-level visual characteristics without reproducing training images. Proactive dataset-use auditing plants a shared signal in a dataset before rel…
Ava Pun, Kevin Dai, Sally Chen, Maxwell Jones, Ruixuan Liu and others · 2026-10-22
Frontier coding agents are becoming increasingly adept at 3D modeling. Yet, they still face challenges when building objects meant to be assembled in the physical world, often creating invalid assemblies with floating, colliding, or disconnected parts. We argue that providing age…
Xiaolin Li, Zihao Huang, Fanpeng Meng, Chen Yang, Guanjun Wu and others · 2026-10-22
Single-image 3D generation has achieved high fidelity on curated benchmarks, yet degrades sharply on real-world images with uneven illumination, blur, and occlusions. Purifying such inputs requires deciding when to intervene and preserving the visual cues needed for 3D generation…
Namitha Guruprasad, Abhay Yadav, Cheng Peng, Rama Chellappa, Anand Bhattad · 2026-10-22
Monocular models recover 3D geometry from a single image in one pass, but most assume a pinhole camera and produce distorted geometry on the wide-angle imagery produced by fisheye and panoramic lenses. Camera-aware models remove this assumption by predicting a per-pixel ray field…
Matteo Fusconi, Alex Costanzino, Pierluigi Zama Ramirez, Luigi Di Stefano · 2026-10-22
Learnable Representations (LRs) can fit parametric families of functions to diverse kinds of signals. These emergent neural-native data formats are gathering interest in the scientific community due to their compactness, resolution-agnosticism and amenability to direct neural pro…
Shuzhou Yang, Lanqing Guo, Lingen Li, Weiqi Li, Zhao Zhong and others · 2026-10-22
Video object removal and injection are reciprocal editing operations between object-present and object-absent video states, yet they differ substantially in training difficulty. Removal can be effectively bootstrapped from video inpainting and further adapted to erase object-rela…
Chenxi Song, Yanming Yang, Tong Zhao, Ruibo Li, Joey Tianyi Zhou and others · 2026-10-22
Video diffusion models have learned rich 3D/4D priors, making them promising for scene generation and video re-rendering. However, their use in spatial tasks is limited by imprecise camera control, spatial and temporal inconsistencies, and entangled camera motion with scene dynam…
Zunnan Xu, Shangchen Zhou, Yihang Luo, Chen Change Loy · 2026-10-22
Feed-forward models accurately estimate camera motion and 3D geometry from short video windows. However, computational and memory costs prevent direct inference on sequences containing thousands of frames. Long videos must therefore be processed as overlapping chunks. This divisi…
Jinyu Zhang, Haitao Lin, Jiashu Hou, Xiangyang Xue, Yanwei Fu · 2026-10-22
This paper studies category-level RGB-D object pose estimation, which recovers an object's 3D rotation and translation without instance-specific CAD models or reference views. This task is highly ambiguous due to intra-class variations, symmetries, and partial observations. Curre…
Merve Kocabas, Benjamin A. Burns, Andreas Geiger, Kent Gauen, Sara Fridovich-Keil · 2026-10-22
Diffusion models have become strong priors for solving inverse problems. However, nonlinear inverse problems such as phase retrieval remain challenging when multiple measurement-consistent solutions are distinguishable only by the prior; we call such measurements ambiguous. Exist…
Ilan Theodoro, Jordão Bragantini, Loïc A. Royer · 2026-10-22
Large language models have shown outstanding performance on text-first tasks such as coding, math, and writing. Recent efforts are shifting models' training to include scientific problems that often live in highly specialized domains beyond text, such as protein structure and bio…
Xuhui Zuo, Chenjie Cao, Tengfei Wang, Junta Wu, Yisu Zhang and others · 2026-10-22
Generating 360-degree panoramas requires both local perspective fidelity and global spherical continuity. Existing representations face a trade-off: equirectangular projection (ERP) enables seamless panorama modeling but suffers from severe distortion and a domain gap to pre-trai…
Jihoon Hong, Alireza Kheirandish, Rohan Sanda, Sara Fridovich-Keil · 2026-10-22
Local anomaly detection is the task of identifying spatially confined anomalous or out-of-distribution (OOD) regions within an otherwise in-distribution (ID) image. Most existing methods are designed for a specific context, with a strong focus on industrial defect detection, wher…
Claudia Giardina, Montse Pardàs, Verónica Vilaplana · 2026-10-22
Synthetic biparametric MRI (bpMRI) may help alleviate the limited availability of large and representative prostate MRI datasets for deep learning applications. In this work, we present a conditional 3D diffusion framework for anatomy-conditioned synthesis of complete prostate bp…
Gabriel Oliveira-Stahl, Anna Schroder, James Moggridge, Hamza A. Salhab, Caroline Micallef and others · 2026-10-22
Accurate hippocampal segmentation can be a useful tool for diagnosing and monitoring neurological conditions such as Alzheimer's disease and epilepsy. While numerous automated segmentation methods exist, their clinical adoption remains limited. Reliable uncertainty assessment can…
Advait Gupta, Sachin Konan, Tom Yin, Gabriel Sarch, Zhuang Liu · 2026-10-22
Vision-language models (VLMs) can perform a broad range of tasks across diverse settings, yet their performance in agentic contexts remains poorly understood. Although online evaluations in simulators and real-world environments are essential for measuring interactive agent perfo…
Zixin Wang, James Hopgood, Mike Davies · 2026-10-22
Multibeam imaging sonar produces intensity images degraded by coherent speckle and system-induced blur, while clean reflectivity targets are rarely available. Existing despeckling methods often rely on simplified intensity-domain noise models, synthetic clean targets, or blind-sp…
Khaled Waleed Dawoud, Muhammad Zaigham Zaheer, Khan Muhammad, Muhammad Haris Khan · 2026-10-22
Vision-Language Models (VLMs) have shown strong potential for video anomaly detection, but dense frame-level inference makes them impractical for real-time deployment. Existing acceleration commonly relies on uniform sampling, which ignores content dynamics and can either waste c…
Di Yang, Xiaochang Li, Muyang Liu, Yufei Wang, Yanhai Xiong · 2026-10-22
Many questions about a video concern one physical object. Where does the ball end up after the cups are shuffled? Which card is the queen? How often was the mug covered? Video-language models (Video-LMs) recognise such objects in single frames but do not keep them apart over time…
Ruicong Liu, Liangyang Ouyang, Fengbo Lan, Zhixiang Wang, Kaipeng Zhang · 2026-10-22
AI coding agents can now build small playable games in minutes, but the results usually look like programmer art: gray blockouts, colored geometric primitives, and flat semantic blobs. We present AnyGameRenderer, a video-to-video generative renderer that turns such footage into h…
Minkyun Seo, Hyungtae Lim, Jaesik Park · 2026-10-22
Point cloud transformers aim to capture detailed local geometry and relationships across a scene at a manageable computational cost. Two common approaches are window attention and global attention. They differ in how they enable scene-wide interaction, which refers to information…
Eun Sun Lee, Minkyun Seo, Gwangtak Bae, Junho Kim, Seunggu Kang and others · 2026-10-22
A conventional embodied agent in an indoor environment builds a map by accumulating noisy real-world measurements and results from heavy inference to guide navigation. While the detailed measurements may differ due to scene changes or sensor settings, the unique topological struc…
Yufei Tong, Guanjie Cheng, Tianle Wu, Leilei Zhang, Hang Zheng and others · 2026-10-22
Visual document understanding is essential for acquiring knowledge from visually rich documents and is attracting growing research interest. Existing surveys emphasize architectures or technical approaches, with limited attention to how task bottlenecks shape technical choices an…
Tianming Liang, Junyi Pan, Yuxi Li, Canmiao Fu, Zhipeng Huang and others · 2026-10-22
Existing vision-language models (VLMs) remain unreliable for fine-grained visual perception. In this report, we present WeVisOne-VL (WeChat Vision All-in-One), a powerful VLM that unifies object-level and pixel-level perception through structured next-token prediction. It support…
Xinyang Lu, Shengzhe Wei, Sheng Tang, Weiqi Zhang, Juntong Fang and others · 2026-10-22
Local feature matching is typically formulated for image pairs, although structure-from-motion and visual localization commonly match one reference image against many retrieved or covisible neighbours. Applying a pairwise matcher independently to these centre-neighbour edges dupl…
Wei Zhang, Ying Feng, Mengtong Wu, Shiqiang Gong, Huaqi Zhang and others · 2026-10-22
4D scene reconstruction requires robust handling of dynamic objects, yet existing streaming methods commonly assume static scenes, leading to pose drift and ghosting artifacts over long sequences. We introduce Stream4D, a training-free, motion-decoupled streaming reconstruction f…
Yue Zhou, Shujun Zhao, Xue Yang, Ruigang Li, Tianwen Zhang and others · 2026-10-22
During the deep learning era, innovations in remote sensing (RS) vision models primarily focused on optimizing network architectures for specific tasks and conducting end-to-end training. However, with the advent of the Vision-Language Models (VLMs) era, constrained by substantia…
Niklas Berndt, Xianghui Xie, Enes Duran, Yixiao Wang, Gerard Pons-Moll · 2026-10-22
Synthesizing physically grounded dexterous hand-object interactions is important for VR/AR, gaming, and robotics, yet remains challenging because subtle contact dynamics, diverse object geometries, and target trajectories must be jointly respected while maintaining natural grasps…
Thanh-Khoi Nguyen, Thien-Phuc Tran, Minh-Triet Tran · 2026-10-22
Online semantic 3D Gaussian Splatting (3DGS) enables open-vocabulary scene understanding from streaming observations. However, existing methods recover geometric context missing from image-derived semantic features using an additionally learned 3D network, incurring extra trainin…
Raffaele Cali, Giuseppe Lando, Rosario Forte, Antonino Furnari · 2026-10-22
Long egocentric videos pose a central challenge for multimodal language models: the visual stream must be compressed into a memory representation that can be searched efficiently while still preserving the evidence needed for question answering. Building on an online textual-memo…
Changseon Yu, Hyeokjun Kweon · 2026-10-22
Training-free personalization adapts a frozen vision-language model (VLM) to recognize user-defined concepts from only a few exemplars by retrieving concept entries at inference time. While recent retriever-based methods enrich each concept with descriptive evidence, they largely…
Sidhart Sami, Ali Sharjeel, Sri Atluri, Miao Zhao, Caroline Roney and others · 2026-10-22
Limited tumour visibility on intra-operative images complicates surgical navigation, including liver hepatocellular carcinoma (HCC) targeting on computed tomography (CT) imaging. This makes labelled datasets difficult to curate for deep learning, and transferring pre-operative de…
Weihao Gao · 2026-10-22
Real-time polyp segmentation in computer-assisted colonoscopy is hampered by the difficulty of deploying high-accuracy models under strict latency budgets. Frame skipping, which performs inference every K frames and reuses or interpolates the rest, improves throughput but introdu…
Ariel Lapid, Yuval Haitman, Reuven Peretz, Arnon Netzer, Idit Diamant · 2026-10-22
Low-light image enhancement (LLIE) aims to recover well-exposed and perceptually faithful images from severely degraded observations. Recent diffusion-based generative methods achieve strong perceptual quality by leveraging powerful image priors, but their iterative sampling incu…
Wenhua Jin, Tiancheng Chen, Sheng Tang, Jiahao Li, Yupeng Liu and others · 2026-10-22
Moving object segmentation is conventionally formulated at the sequence and object level, marking an entire instance as moving once it moves anywhere in a video. Recent instantaneous formulations distinguish moving from stationary intervals, but still generate masks at the object…
Ronald Fecso, José Morano, Botond Fazekas, Paul Widmann-Sedlnitzky, Dorota Himel and others · 2026-10-22
Multimodal large language models (MLLMs) can answer clinical questions about medical images, but trustworthy use requires visual grounding: models should localize the pathology they report rather than rely on spurious shortcuts. Whether MLLMs can visually ground clinical findings…
Hossein Resani, Javen Qinfeng Shi · 2026-10-22
Joint-embedding predictive architectures (JEPAs) learn world models in latent space, enabling efficient planning but leaving their states opaque. We introduce Inside-JEPA, which places relational channels for ordered entity pairs inside the JEPA latent state and shows that an inv…
GET https://store.agentexchange.work/gw/papers/latest?cat=cs.CV&limit=25 (0.003 USD per call). Catalogue