3D 视觉

2509.26498 2025-10-01 cs.CV 57%

DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidance

Jijun Xiang, Longliang Liu, Xuan Zhu, Xianqi Wang, Min Lin, Xin Yang

机构 * School of Electronic Information and Communications, Huazhong University of Science and Technology（电子信息与通信学院，华中科技大学）

专题命中三维重建：3D reconstruction(abstract)；分类 cs.CV

Comments 15 pages, 16 figures

2509.25788 2025-10-01 cs.LG 50%

From Cheap Geometry to Expensive Physics: Elevating Neural Operators via Latent Shape Pretraining

Zhizhou Zhang, Youjia Wu, Kaixuan Zhang, Yanjia Wang

机构 * Corporate Research Bosch (China) Investment Co., Ltd.（博世（中国）投资有限公司）

专题命中三维重建：point cloud(abstract)

2508.15372 2025-10-01 cs.CV cs.AI cs.GR 73%

Image-Conditioned 3D Gaussian Splat Quantization

Xinshuang Liu, Runfa Blark Li, Keito Suzuki, Truong Nguyen

机构 * University of California, San Diego（加州大学圣地亚哥分校）

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)；3DGS(abstract)；分类 cs.CV、cs.GR

2509.25603 2025-10-01 cs.CV 70%

GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification

Yijia Weng, Zhicheng Wang, Songyou Peng, Saining Xie, Howard Zhou, Leonidas J. Guibas

机构 * Stanford University（斯坦福大学）； Google DeepMind（谷歌DeepMind）

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)；3DGS(abstract)；分类 cs.CV

2412.07494 2025-10-01 cs.CV 70%

ResGS: Residual Densification of 3D Gaussian for Efficient Detail Recovery

Yanzhe Lyu, Kai Cheng, Xin Kang, Xuejin Chen

机构 * MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition（脑启发式智能感知与认知联合实验室）

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)；novel view synthesis(abstract)；分类 cs.CV

2509.26055 2025-10-01 cs.GR cs.CV cs.LG 62%

GaussEdit: Adaptive 3D Scene Editing with Text and Image Prompts

Zhenyu Shu, Junlong Yu, Kai Chao, Shiqing Xin, Ligang Liu

机构 * School of Computer and Data Engineering, NingboTech University（计算机与数据工程学院，宁波科技学院）； Ningbo Institute, Zhejiang University（浙江大学宁波学院）； School of Software Technology, Zhejiang University（软件技术学院，浙江大学）； School of Big Data and Artificial Intelligence Management, Xi’an Jiaotong University（大数据与人工智能管理学院，西安交通大学）； School of Computer Science and Technology, ShanDong University（计算机科学与技术学院，山东大学）； Graphics & Geometric Computing Laboratory, School of Mathematical Sciences, University of Science and Technology of China（图形与几何计算实验室，数学科学学院，中国科学技术大学）

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)；分类 cs.CV、cs.GR

Journal ref IEEE Transactions on Visualization and Computer Graphics. 2025

2509.25984 2025-10-01 cs.RO 57%

S$^3$E: Self-Supervised State Estimation for Radar-Inertial System

Shengpeng Wang, Yulong Xie, Qing Liao, Wei Wang

机构 * Huazhong University of Science and Technology（华中科技大学）； Harbin Institute of Technology（哈尔滨工业大学）； Wuhan University（武汉大学）

专题命中点云：point cloud(abstract)；分类 cs.RO

2509.25970 2025-10-01 cs.CV 57%

PinPoint3D: Fine-Grained 3D Part Segmentation from a Few Clicks

Bojun Zhang, Hangjian Ye, Hao Zheng, Jianzheng Huang, Zhengyu Lin, Zhenhong Guo, Feng Zheng

机构 * Department of Computer Science and Engineering（计算机科学与工程系）

专题命中点云：point cloud(abstract)；分类 cs.CV

Comments 15 pages, 12 figures, conference

2509.21145 2025-10-01 cs.RO 57%

DAGDiff: Guiding Dual-Arm Grasp Diffusion to Stable and Collision-Free Grasps

Md Faizal Karim, Vignesh Vembar, Keshab Patra, Gaurav Singh, K Madhava Krishna

机构 * Robotics Research Center, IIIT Hyderabad（IIIT海得拉巴机器人研究中心）； Brown University（布朗大学）

专题命中点云：point cloud(abstract)；分类 cs.RO

2509.16999 2025-10-01 cs.LG math.AT 50%

Persistence Spheres: Bi-continuous Representations of Persistence Diagrams

Matteo Pegoraro

机构 * Department of Mathematics, KTH（数学系，皇家理工学院）

专题命中点云：point cloud(abstract)

2507.15748 2025-10-01 cs.CV 70%

CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction

Jisu Shin, Richard Shaw, Seunghyun Shin, Zhensong Zhang, Hae-Gon Jeon, Eduardo Perez-Pellitero

机构 * Huawei Noah’s Ark Lab（华为诺亚实验室）； GIST AI Graduate School（GIST人工智能研究生院）； Yonsei University（延世大学）

专题命中新视角合成：3D reconstruction(abstract)；novel view synthesis(abstract)；分类 cs.CV

2509.25966 2025-10-01 cs.RO 57%

MUVLA: Learning to Explore Object Navigation via Map Understanding

Peilong Han, Fan Jia, Min Zhang, Yutao Qiu, Hongyao Tang, Yan Zheng, Tiancai Wang, Jianye Hao

机构 * Dexmal

专题命中空间理解：spatial understanding(abstract)；分类 cs.RO

2509.06266 2025-10-01 cs.CV 57%

Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes

Mohsen Gholami, Ahmad Rezaei, Zhou Weimin, Sitong Mao, Shunbo Zhou, Yong Zhang, Mohammad Akbari

机构 * Huawei Technologies Canada（华为技术加拿大分公司）； Huawei Cloud Project Page Code Ego3D-Bench（华为云项目页面代码Ego3D-Bench）

专题命中空间理解：spatial understanding(abstract)；分类 cs.CV

1. 三维重建 2 篇

DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidance

From Cheap Geometry to Expensive Physics: Elevating Neural Operators via Latent Shape Pretraining

2. Gaussian Splatting 4 篇

Image-Conditioned 3D Gaussian Splat Quantization

GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification

ResGS: Residual Densification of 3D Gaussian for Efficient Detail Recovery

GaussEdit: Adaptive 3D Scene Editing with Text and Image Prompts

3. 点云 4 篇

S$^3$E: Self-Supervised State Estimation for Radar-Inertial System

PinPoint3D: Fine-Grained 3D Part Segmentation from a Few Clicks

DAGDiff: Guiding Dual-Arm Grasp Diffusion to Stable and Collision-Free Grasps

Persistence Spheres: Bi-continuous Representations of Persistence Diagrams

4. 新视角合成 1 篇

CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction

5. 空间理解 2 篇

MUVLA: Learning to Explore Object Navigation via Map Understanding

Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes