3D 视觉

OSMa-Bench: Evaluating Open Semantic Mapping Under Varying Lighting Conditions

OSMa-Bench: 评估开放语义映射在不同光照条件下的性能

Maxim Popov, Regina Kurkova, Mikhail Iumanov, Jaafar Mahmoud, Sergey Kolyubin

机构 * Biomechatronics and Energy-Efficient Robotics (BE2R) Lab, ITMO University（生物机电学与节能机器人实验室，ITMO大学） 纠错

专题命中 SLAM与定位 ：3D reconstruction(abstract)；分类 cs.CV、cs.RO

AI总结 OSMa-Bench通过评估不同光照条件下语义映射算法的性能，推动了更鲁棒的机器人系统发展。

Comments Project page: https://be2rlab.github.io/OSMa-Bench/

Journal ref 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hangzhou, China, 2025, pp. 10786-10791

PERSEUS: Perception with Semantic Endoscopic Understanding and SLAM

PERSEUS：具有语义内窥镜理解和SLAM的感知

Ayberk Acar, Fangjie Li, Susheela Sharma Stern, Lidia Al-Zogbi, Hao Li, Kanyifeechukwu Jane Oguine, Dilara Isik, Brendan Burkhart, Jesse F. d'Almeida, Robert J. Webster, Ipek Oguz, Jie Ying Wu

专题命中 SLAM与定位 ：3D reconstruction(abstract)；分类 cs.CV、cs.RO

AI总结 PERSEUS提出了一种结合语义分割与实时单目SLAM的感知管道，用于自然开口手术，实现高精度的场景理解和手术指导。

Comments 13 pages, 6 figures, 2 tables. Under review for The 17th International Conference on Information Processing in Computer-Assisted Interventions (IPCAI 2026)

SDT-6D: Fully Sparse Depth-Transformer for Staged End-to-End 6D Pose Estimation in Industrial Multi-View Bin Picking

SDT-6D: 全稀疏深度-变换器用于工业多视角堆叠取料的端到端6D姿态估计

Nico Leuze, Maximilian Hoh, Samed Doğan, Nicolas R. -Peña, Alfred Schoettl

机构 * Institute for Applications of Machine Learning and Intelligent Systems（机器学习与智能系统应用研究所） ； University of Applied Science Munich（慕尼黑应用科学大学） 纠错

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

AI总结 SDT-6D提出了一种基于稀疏深度-变换器的端到端6D姿态估计方法，通过分阶段热图机制和密度感知稀疏变换器块，实现高分辨率下的高效姿态预测。

Comments Accepted to WACV 2026. Preprint version

Dynamic Visual SLAM using a General 3D Prior

利用通用3D先验的动态视觉SLAM

Xingguang Zhong, Liren Jin, Marija Popović, Jens Behley, Cyrill Stachniss

机构 * Center for Robotics, University of Bonn（博恩大学机器人中心） ； MAVLab, TU Delft（代尔夫特理工大学MAVLab） ； Lamarr Institute for Machine Learning and Artificial Intelligence（兰玛尔人工智能与机器学习研究所） 纠错

专题命中 SLAM与定位 ：3D reconstruction(abstract)；分类 cs.CV、cs.RO

AI总结 本文提出一种利用通用3D先验的单目视觉SLAM系统，通过结合前馈重建模型与集束调整，提升动态场景中相机姿态估计的鲁棒性。

Comments 8 pages

OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding

Artem Moroz, Vít Zeman, Martin Mikšík, Elizaveta Isianova, Miroslav David, Pavel Burget, Varun Burde

机构 * Czech Institute of Informatics, Robotics and Cybernetics（捷克信息学、机器人学与自动化研究所） ； Czech Technical University in Prague（布拉格捷克技术大学） 纠错

专题命中 SLAM与定位 ：NeRF(abstract)；分类 cs.CV、cs.RO

PALMS+: Modular Image-Based Floor Plan Localization Leveraging Depth Foundation Model

Yunqian Cheng, Benjamin Princen, Roberto Manduchi

机构 * University of California, Santa Cruz（加州大学圣克ruz分校） 纠错

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted to IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026, Application Track. Main paper: 8 pages, 5 figures. Supplementary material included

Semi-distributed Cross-modal Air-Ground Relative Localization

Weining Lu, Deer Bin, Lian Ma, Ming Ma, Zhihao Ma, Xiangyang Chen, Longfei Wang, Yixiao Feng, Zhouxian Jiang, Yongliang Shi, Bin Liang

机构 * Beijng National Research Center for Information Science and Technology（北京国家信息科学与技术研究中心） ； Qiyuan Lab（启元实验室） ； JiangHuai Advanced Technology Center（江淮先进技术中心） 纠错

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 7 pages, 3 figures. Accepted by IROS 2025

SuperEx: Enhancing Indoor Mapping and Exploration using Non-Line-of-Sight Perception

Kush Garg, Akshat Dave

机构 * Department of Applied Mathematics, Delhi Technological University（应用数学系，德里技术大学） ； Stony Brook University（石溪大学） 纠错

专题命中 SLAM与定位 ：3D reconstruction(abstract)；分类 cs.CV、cs.RO

Comments 8 pages, 9 Figures , Project webpage: https://super-ex.github.io/

Non-Rigid Structure-from-Motion via Differential Geometry with Recoverable Conformal Scale

Yongbo Chen, Yanhao Zhang, Shaifali Parashar, Liang Zhao, Shoudong Huang

机构 * University of Technology Sydney（技术大学悉尼大学） ； Shanghai Jiao Tong University（上海交通大学） ； University of Edinburgh（爱丁堡大学） ； Institut National des Sciences Appliquées de Lyon (LIRIS, INSA-Lyon)（里尔大学 Lyon（LIRIS，INSA-Lyon）） 纠错

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

InterKey: Cross-modal Intersection Keypoints for Global Localization on OpenStreetMap

Nguyen Hoang Khoi Tran, Julie Stephany Berrio, Mao Shan, Stewart Worrall

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 8 pages, 5 figures

GRS-SLAM3R: Real-Time Dense SLAM with Gated Recurrent State

Guole Shen, Tianchen Deng, Yanbo Wang, Yongtao Chen, Yilin Shen, Jiuming Liu, Jingchuan Wang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Institute of Medical Robotics（医疗机器人研究所） ； School of Automation and Intelligent Sensing（自动化与智能感知学院） ； Key Laboratory of System Control and Information Processing（系统控制与信息处理重点实验室） ； Ministry of Education of China（中华人民共和国教育部） 纠错

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Object Pose Estimation through Dexterous Touch

Amir-Hossein Shahidzadeh, Jiyue Zhu, Kezhou Chen, Sha Yi, Cornelia Fermüller, Yiannis Aloimonos, Xiaolong Wang

机构 * Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente（电子工程、数学和计算机科学学院，代尔夫特理工大学） ； Department of Electrical Engineering, Wright State University（电气工程系，怀特州立大学） 纠错

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments

Dmitry Yudin

机构 * Moscow Institute of Physics and Technology（莫斯科物理技术学院） ； AIRI 纠错

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 29 pages, 3 figures, 13 tables. Preprint of the accepted article in Optical Memory and Neural Network Journal

Pose Estimation from Camera Images for Underwater Inspection

Luyuan Peng, Hari Vishnu, Mandar Chitre, Yuen Min Too, Bharath Kalyan, Rajat Mishra, Soo Pieng Tan

专题命中 SLAM与定位 ：novel view synthesis(abstract)；分类 cs.CV、cs.RO

Comments Submitted to IEEE Journal of Oceanic Engineering

REGRACE: A Robust and Efficient Graph-based Re-localization Algorithm using Consistency Evaluation

Débora N. P. Oliveira, Joshua Knights, Sebastián Barbas Laina, Simon Boche, Wolfram Burgard, Stefan Leutenegger

机构 * Artificial Intelligence and Robotics Lab, University of Technology of Nuremberg (UTN)（人工智能与机器人实验室，图恩技术大学（UTN）） ； CSIRO Robotics, DATA61, and Queensland University of Technology (QUT)（CSIRO机器人，DATA61，昆士兰理工大学（QUT）） ； Mobile Robotics Lab, Technical University of Munich (TUM)（移动机器人实验室，慕尼黑技术大学（TUM）） ； Munich Institute of Robotics and Machine Intelligence (MIRMI)（慕尼黑机器人与机器智能研究所（MIRMI）） ； Mobile Robotics Lab, ETH Zurich（移动机器人实验室，苏黎世联邦理工学院） 纠错

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted to IROS2025

Multimodal HD Mapping for Intersections by Intelligent Roadside Units

Zhongzhang Chen, Miao Fan, Shengtong Xu, Mengmeng Yang, Kun Jiang, Xiangzeng Liu, Haoyi Xiong

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted by ITSC'25

MK-Pose: Category-Level Object Pose Estimation via Multimodal-Based Keypoint Learning

Yifan Yang, Peili Song, Enfan Lan, Dong Liu, Jingtai Liu

机构 * Institute of Robotics and Automatic Information System（机器人与自动信息系统研究所） ； Tianjin Key Laboratory of Intelligent Robotics（天津智能机器人重点实验室） ； TBI center（TBI中心） ； Nankai University（南开大学） 纠错

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

You Only Estimate Once: Unified, One-stage, Real-Time Category-level Articulated Object 6D Pose Estimation for Robotic Grasping

Jingshun Huang, Haitao Lin, Tianyu Wang, Yanwei Fu, Yu-Gang Jiang, Xiangyang Xue

机构 * Fudan University（复旦大学） ； Tencent Robotics X Lab（腾讯机器人X实验室） 纠错

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments To appear in ICRA 2025

An Efficient Method for Accurate Pose Estimation and Error Correction of Cuboidal Objects

Utsav Rai, Hardik Mehta, Vismay Vakharia, Aditya Choudhary, Amit Parmar, Rolif Lima, Kaushik Das

机构 * Embedded Systems and robotics, Tata Consultancy Services, Research and Innovation（嵌入式系统与机器人，塔塔咨询服务，研究与创新） 纠错

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted in IEEE/RSJ IROS 2022 Workshop on Mobile Manipulation and Embodied Intelligence (MOMA)

Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D

Sergio Arnaud, Paul McVay, Ada Martin, Arjun Majumdar, Krishna Murthy Jatavallabhula, Phillip Thomas, Ruslan Partsey, Daniel Dugas, Abha Gejji, Alexander Sax, Vincent-Pierre Berges, Mikael Henaff, Ayush Jain, Ang Cao, Ishita Prasad, Mrinal Kalakrishnan, Michael Rabbat, Nicolas Ballas, Mido Assran, Oleksandr Maksymets, Aravind Rajeswaran, Franziska Meier

机构 * FAIR at Meta（Meta 的 FAIR） 纠错

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model

Jian Liu, Wei Sun, Hui Yang, Jin Zheng, Zichen Geng, Hossein Rahmani, Ajmal Mian

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted by ICRA'25

HIF: Height Interval Filtering for Efficient Dynamic Points Removal

Shufang Zhang, Tao Jiang, Jiazheng Wu, Ziyu Meng, Ziyang Zhang, Shan An

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Improving Monocular Visual-Inertial Initialization with Structureless Visual-Inertial Bundle Adjustment

Junlin Song, Antoine Richard, Miguel Olivares-Mendez

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted by ICRA 2025

InCrowd-VI: A Realistic Visual-Inertial Dataset for Evaluating SLAM in Indoor Pedestrian-Rich Spaces for Human Navigation

Marziyeh Bamdad, Hans-Peter Hutter, Alireza Darvishy

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 24 pages, 8 figures, 6 tables

CMRNext: Camera to LiDAR Matching in the Wild for Localization and Extrinsic Calibration

Daniele Cattaneo, Abhinav Valada

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments Accepted to IEEE Transactions on Robotics (T-RO), 2025

Volumetric Mapping with Panoptic Refinement via Kernel Density Estimation for Mobile Robots

Khang Nguyen, Tuan Dang, Manfred Huber

专题命中 SLAM与定位 ：3D reconstruction(abstract)；分类 cs.CV、cs.RO

MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM

Vladimir Yugay, Theo Gevers, Martin R. Oswald

专题命中 SLAM与定位 ：novel view synthesis(abstract)；分类 cs.CV、cs.RO

Tightly-Coupled, Speed-aided Monocular Visual-Inertial Localization in Topological Map

Chanuk Yang, Hayeon O, Kunsoo Huh

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

SPACE: 3D Spatial Co-operation and Exploration Framework for Robust Mapping and Coverage with Multi-Robot Systems

Sai Krishna Ghanta, Ramviyas Parasuraman

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.CV、cs.RO

3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction

Jongmin Lee, Minsu Cho

专题命中 SLAM与定位 ：3D vision(abstract)；分类 cs.CV、cs.RO

Comments Accepted to NeurIPS 2024, Project webpage at http://cvlab.postech.ac.kr/research/3D_EquiPose