Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds.

Xiaoyang Wu 0002 The University of Hong Kong, SAR, China https://orcid.org/0009-0002-2277-7104 Xiaoyang Wu Xiaoyang Wu 0001 University of Zhejiang, Hangzhou, China Xiaoyang Wu 0003 Beijing Jiaotong University, Beijing, China Xiaoyang Wu 0004 Harbin Institute of Technology, Shenzhen, China https://orcid.org/0000-0003-0155-1595 https://ieeexplore.ieee.org/author/37089195093 Xiaoyang Wu 0005 Qufu Normal University, Qufu, China Xiaoyang Wu 0006 Saarland University, Saarbrücken, Germany Polytechnic University of Bari, Bari, Italy Xiaoyang Wu 0007 Hikvision Research Institute, Hangzhou, China

Xianzhe Fan Shengliang Deng Xiaoyang Wu 0002 Yuxiang Lu Zhuoling Li Mi Yan Yujia Zhang 0003 Zhizheng Zhang 0011 He Wang Hengshuang Zhao Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds. 2026 February abs/2602.00807 CoRR https://doi.org/10.48550/arXiv.2602.00807 db/journals/corr/corr2602.html#abs-2602-00807 streams/journals/corr

Yujia Zhang 0003 Xiaoyang Wu 0002 Yunhan Yang Xianzhe Fan Han Li Yuechen Zhang Zehao Huang Naiyan Wang Hengshuang Zhao Utonia: Toward One Encoder for All Point Clouds. 2026 March abs/2603.03283 CoRR https://doi.org/10.48550/arXiv.2603.03283 db/journals/corr/corr2603.html#abs-2603-03283 streams/journals/corr

Yixing Lao Xuyang Bai Xiaoyang Wu 0002 Nuoyuan Yan Zixin Luo Tian Fang Jean-Daniel Nahmias Yanghai Tsin Shiwei Li 0001 Hengshuang Zhao Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting. 2026 March abs/2603.25745 CoRR https://doi.org/10.48550/arXiv.2603.25745 db/journals/corr/corr2603.html#abs-2603-25745 streams/journals/corr

Haoyi Zhu Honghui Yang Xiaoyang Wu 0002 Di Huang Sha Zhang 0002 Xianglong He Hengshuang Zhao Chunhua Shen Yu Qiao 0001 Tong He 0001 Wanli Ouyang PonderV2: Improved 3D Representation With a Universal Pre-Training Paradigm. 6550-6565 2025 August 47 IEEE Trans. Pattern Anal. Mach. Intell. 8 https://doi.org/10.1109/TPAMI.2025.3561598 db/journals/pami/pami47.html#ZhuYWHZHZSQHO25 streams/journals/pami

Xiaoyang Wu 0002 Daniel DeTone Duncan P. Frost Tianwei Shen Chris Xie Nan Yang Jakob J. Engel Richard A. Newcombe Hengshuang Zhao Julian Straub Sonata: Self-Supervised Learning of Reliable Point Representations. 22193-22204 2025 CVPR https://openaccess.thecvf.com/content/CVPR2025/html/Wu_Sonata_Self-Supervised_Learning_of_Reliable_Point_Representations_CVPR_2025_paper.html https://doi.org/10.1109/CVPR52734.2025.02067 conf/cvpr/2025 db/conf/cvpr/cvpr2025.html#0002DFSXYENZS25 Zhuoling Li Liangliang Ren Jinrong Yang Yong Zhao Xiaoyang Wu 0002 Zhenhua Xu 0003 Xiang Bai Hengshuang Zhao VIP: Vision Instructed Pre-training for Robotic Manipulation. 2025 ICML https://proceedings.mlr.press/v267/li25by.html https://openreview.net/forum?id=ccUNMIbpcf conf/icml/2025 db/conf/icml/icml2025.html#LiRYZ00BZ25

Xiaoyang Wu 0002 Daniel DeTone Duncan P. Frost Tianwei Shen Chris Xie Nan Yang Jakob J. Engel Richard A. Newcombe Hengshuang Zhao Julian Straub Sonata: Self-Supervised Learning of Reliable Point Representations. 2025 March abs/2503.16429 CoRR https://doi.org/10.48550/arXiv.2503.16429 db/journals/corr/corr2503.html#abs-2503-16429 streams/journals/corr

Xi Chen 0119 Mingkang Zhu Shaoteng Liu Xiaoyang Wu 0002 Xiaogang Xu 0002 Yu Liu 0063 Xiang Bai Hengshuang Zhao MiCo: Multi-image Contrast for Reinforcement Visual Reasoning. 2025 June abs/2506.22434 CoRR https://doi.org/10.48550/arXiv.2506.22434 db/journals/corr/corr2506.html#abs-2506-22434 streams/journals/corr

Yunhan Yang Shuo Chen Yukun Huang Xiaoyang Wu 0002 Yuan-Chen Guo Edmund Y. Lam Hengshuang Zhao Tong He 0001 Xihui Liu DreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content Generation. 2025 July abs/2507.02299 CoRR https://doi.org/10.48550/arXiv.2507.02299 db/journals/corr/corr2507.html#abs-2507-02299 streams/journals/corr

Zhening Huang Xiaoyang Wu 0002 Fangcheng Zhong Hengshuang Zhao Matthias Nießner Joan Lasenby LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans. 2025 July abs/2507.02861 CoRR https://doi.org/10.48550/arXiv.2507.02861 db/journals/corr/corr2507.html#abs-2507-02861 streams/journals/corr

Zhuoling Li Xiaoyang Wu 0002 Zhenhua Xu 0003 Hengshuang Zhao Train Once, Deploy Anywhere: Realize Data-Efficient Dynamic Object Manipulation. 2025 August abs/2508.14042 CoRR https://doi.org/10.48550/arXiv.2508.14042 db/journals/corr/corr2508.html#abs-2508-14042 streams/journals/corr

Yujia Zhang 0003 Xiaoyang Wu 0002 Yixing Lao Chengyao Wang Zhuotao Tian Naiyan Wang Hengshuang Zhao Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations. 2025 October abs/2510.23607 CoRR https://doi.org/10.48550/arXiv.2510.23607 db/journals/corr/corr2510.html#abs-2510-23607 streams/journals/corr

Zhangyang Qi Jiaqi Wang 0003 Xiaoyang Wu 0002 Hengshuang Zhao OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detection. 1188-1197 2024 3DV https://doi.org/10.1109/3DV62453.2024.00098 conf/3dim/2024 db/conf/3dim/3dv2024.html#QiWWZ24 Xiaoyang Wu 0002 Li Jiang 0009 Peng-Shuai Wang Zhijian Liu Xihui Liu Yu Qiao 0001 Wanli Ouyang Tong He 0001 Hengshuang Zhao Point Transformer V3: Simpler, Faster, Stronger. 4840-4851 2024 CVPR https://doi.org/10.1109/CVPR52733.2024.00463 conf/cvpr/2024 db/conf/cvpr/cvpr2024.html#00020WLL0O0Z24 Chengyao Wang Li Jiang 0009 Xiaoyang Wu 0002 Zhuotao Tian Bohao Peng Hengshuang Zhao Jiaya Jia GroupContrast: Semantic-Aware Self-Supervised Representation Learning for 3D Understanding. 4917-4928 2024 CVPR https://doi.org/10.1109/CVPR52733.2024.00470 conf/cvpr/2024 db/conf/cvpr/cvpr2024.html#Wang00TPZJ24 Yunhan Yang Yukun Huang Xiaoyang Wu 0002 Yuan-Chen Guo Song-Hai Zhang Hengshuang Zhao Tong He 0001 Xihui Liu DreamComposer: Controllable 3D Object Generation via Multi-View Conditions. 8111-8120 2024 CVPR https://doi.org/10.1109/CVPR52733.2024.00775 conf/cvpr/2024 db/conf/cvpr/cvpr2024.html#YangHWGZZ0L24 Youquan Liu Lingdong Kong Xiaoyang Wu 0002 Runnan Chen Xin Li 0110 Liang Pan Ziwei Liu 0002 Yuexin Ma Multi-Space Alignments Towards Universal LiDAR Segmentation. 14648-14661 2024 CVPR https://doi.org/10.1109/CVPR52733.2024.01388 conf/cvpr/2024 db/conf/cvpr/cvpr2024.html#LiuK0CLP0M24 Honghui Yang Sha Zhang 0002 Di Huang Xiaoyang Wu 0002 Haoyi Zhu Tong He 0001 Shixiang Tang Hengshuang Zhao Qibo Qiu Binbin Lin Xiaofei He 0001 Wanli Ouyang UniPAD: A Universal Pre-Training Paradigm for Autonomous Driving. 15238-15250 2024 CVPR https://doi.org/10.1109/CVPR52733.2024.01443 conf/cvpr/2024 db/conf/cvpr/cvpr2024.html#YangZHWZ0TZQL0O24 Xiaoyang Wu 0002 Zhuotao Tian Xin Wen 0004 Bohao Peng Xihui Liu Kaicheng Yu Hengshuang Zhao Towards Large-Scale 3D Representation Learning with Multi-Dataset Point Prompt Training. 19551-19562 2024 CVPR https://doi.org/10.1109/CVPR52733.2024.01849 conf/cvpr/2024 db/conf/cvpr/cvpr2024.html#WuTWPLYZ24 Bohao Peng Xiaoyang Wu 0002 Li Jiang 0009 Yukang Chen Hengshuang Zhao Zhuotao Tian Jiaya Jia OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation. 21305-21315 2024 CVPR https://doi.org/10.1109/CVPR52733.2024.02013 conf/cvpr/2024 db/conf/cvpr/cvpr2024.html#PengWJCZTJ24 Zhangyang Qi Ye Fang Zeyi Sun 0002 Xiaoyang Wu 0002 Tong Wu Jiaqi Wang 0003 Dahua Lin Hengshuang Zhao GPT4Point: A Unified Framework for Point-Language Understanding and Generation. 26407-26417 2024 CVPR https://doi.org/10.1109/CVPR52733.2024.02495 conf/cvpr/2024 db/conf/cvpr/cvpr2024.html#QiF0WW0LZ24 Zhening Huang Xiaoyang Wu 0002 Xi Chen 0119 Hengshuang Zhao Lei Zhu 0003 Joan Lasenby OpenIns3D: Snap and Lookup for 3D Open-Vocabulary Instance Segmentation. 169-185 2024 ECCV (62) https://doi.org/10.1007/978-3-031-73033-7_10 conf/eccv/2024-62 db/conf/eccv/eccv2024-62.html#HuangWCZZL24 streams/conf/eccv Yixing Lao Tao Tang Xiaoyang Wu 0002 Peng Chen Kaicheng Yu Hengshuang Zhao LiT: Unifying LiDAR "Languages" with LiDAR Translator. 2024 NeurIPS http://papers.nips.cc/paper_files/paper/2024/hash/aa76025af7f8d69338c4b5ee29f66e70-Abstract-Conference.html conf/nips/2024 db/conf/nips/neurips2024.html#LaoT0CYZ24

Francis Engelmann Ayça Takmaz Jonas Schult Elisabetta Fedele Johanna Wald Songyou Peng Xi Wang 0021 Or Litany Siyu Tang 0001 Federico Tombari Marc Pollefeys Leonidas J. Guibas Hongbo Tian Chunjie Wang Xiaosheng Yan Bingwen Wang Xuanyang Zhang Xiao Liu Phuc Nguyen Khoi Nguyen 0001 Anh Tran 0001 Cuong Pham 0001 Zhening Huang Xiaoyang Wu 0002 Xi Chen 0119 Hengshuang Zhao Lei Zhu 0003 Joan Lasenby OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding. 2024 abs/2402.15321 CoRR https://doi.org/10.48550/arXiv.2402.15321 db/journals/corr/corr2402.html#abs-2402-15321

Chengyao Wang Li Jiang 0009 Xiaoyang Wu 0002 Zhuotao Tian Bohao Peng Hengshuang Zhao Jiaya Jia GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding. 2024 abs/2403.09639 CoRR https://doi.org/10.48550/arXiv.2403.09639 db/journals/corr/corr2403.html#abs-2403-09639

Bohao Peng Xiaoyang Wu 0002 Li Jiang 0009 Yukang Chen Hengshuang Zhao Zhuotao Tian Jiaya Jia OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation. 2024 abs/2403.14418 CoRR https://doi.org/10.48550/arXiv.2403.14418 db/journals/corr/corr2403.html#abs-2403-14418

Youquan Liu Lingdong Kong Xiaoyang Wu 0002 Runnan Chen Xin Li 0110 Liang Pan Ziwei Liu 0002 Yuexin Ma Multi-Space Alignments Towards Universal LiDAR Segmentation. 2024 abs/2405.01538 CoRR https://doi.org/10.48550/arXiv.2405.01538 db/journals/corr/corr2405.html#abs-2405-01538

Zhangyang Qi Yunhan Yang Mengchen Zhang 0001 Long Xing Xiaoyang Wu 0002 Tong Wu Dahua Lin Xihui Liu Jiaqi Wang 0003 Hengshuang Zhao Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images. 2024 abs/2407.06191 CoRR https://doi.org/10.48550/arXiv.2407.06191 db/journals/corr/corr2407.html#abs-2407-06191 streams/journals/corr

Xiaoyang Wu 0002 Xiang Xu 0009 Lingdong Kong Liang Pan Ziwei Liu 0002 Tong He 0001 Wanli Ouyang Hengshuang Zhao Point Transformer V3 Extreme: 1st Place Solution for 2024 Waymo Open Dataset Challenge in Semantic Segmentation. 2024 abs/2407.15282 CoRR https://doi.org/10.48550/arXiv.2407.15282 db/journals/corr/corr2407.html#abs-2407-15282 streams/journals/corr

Zhuoling Li Liangliang Ren Jinrong Yang Yong Zhao Xiaoyang Wu 0002 Zhenhua Xu 0003 Xiang Bai Hengshuang Zhao VIRT: Vision Instructed Transformer for Robotic Manipulation. 2024 abs/2410.07169 CoRR https://doi.org/10.48550/arXiv.2410.07169 db/journals/corr/corr2410.html#abs-2410-07169 streams/journals/corr

Yunhan Yang Yukun Huang Yuan-Chen Guo Liangjun Lu Xiaoyang Wu 0002 Edmund Y. Lam Yan-Pei Cao Xihui Liu SAMPart3D: Segment Any Part in 3D Objects. 2024 abs/2411.07184 CoRR https://doi.org/10.48550/arXiv.2411.07184 db/journals/corr/corr2411.html#abs-2411-07184 streams/journals/corr

Jiahui Liu 0012 Chirui Chang Jianhui Liu Xiaoyang Wu 0002 Lan Ma Xiaojuan Qi 0001 MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds. 9372-9381 2023 CVPR https://doi.org/10.1109/CVPR52729.2023.00904 conf/cvpr/2023 db/conf/cvpr/cvpr2023.html#LiuCL0MQ23 Xiaoyang Wu 0002 Xin Wen 0004 Xihui Liu Hengshuang Zhao Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning. 9415-9424 2023 CVPR https://doi.org/10.1109/CVPR52729.2023.00908 conf/cvpr/2023 db/conf/cvpr/cvpr2023.html#0002WLZ23 Zhisheng Zhong Jiequan Cui Yibo Yang Xiaoyang Wu 0002 Xiaojuan Qi 0001 Xiangyu Zhang 0005 Jiaya Jia Understanding Imbalanced Semantic Segmentation Through Neural Collapse. 19550-19559 2023 CVPR https://doi.org/10.1109/CVPR52729.2023.01873 conf/cvpr/2023 db/conf/cvpr/cvpr2023.html#ZhongCY0QZJ23 Bohao Peng Zhuotao Tian Xiaoyang Wu 0002 Chengyao Wang Shu Liu 0005 Jingyong Su Jiaya Jia Hierarchical Dense Correlation Distillation for Few-Shot Segmentation. 23641-23651 2023 CVPR https://doi.org/10.1109/CVPR52729.2023.02264 conf/cvpr/2023 db/conf/cvpr/cvpr2023.html#PengTWWLSJ23

Zhisheng Zhong Jiequan Cui Yibo Yang Xiaoyang Wu 0002 Xiaojuan Qi 0001 Xiangyu Zhang 0005 Jiaya Jia Understanding Imbalanced Semantic Segmentation Through Neural Collapse. 2023 abs/2301.01100 CoRR https://doi.org/10.48550/arXiv.2301.01100 db/journals/corr/corr2301.html#abs-2301-01100

Zhening Huang Xiaoyang Wu 0002 Hengshuang Zhao Lei Zhu 0003 Shujun Wang Georgios M. Hadjidemetriou Ioannis K. Brilakis GeoSpark: Sparking up Point Cloud Segmentation with Geometry Clue. 2023 abs/2303.08274 CoRR https://doi.org/10.48550/arXiv.2303.08274 db/journals/corr/corr2303.html#abs-2303-08274

Xiaoyang Wu 0002 Xin Wen 0004 Xihui Liu Hengshuang Zhao Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning. 2023 abs/2303.14191 CoRR https://doi.org/10.48550/arXiv.2303.14191 db/journals/corr/corr2303.html#abs-2303-14191

Bohao Peng Zhuotao Tian Xiaoyang Wu 0002 Chenyao Wang Shu Liu 0005 Jingyong Su Jiaya Jia Hierarchical Dense Correlation Distillation for Few-Shot Segmentation. 2023 abs/2303.14652 CoRR https://doi.org/10.48550/arXiv.2303.14652 db/journals/corr/corr2303.html#abs-2303-14652

Zhangyang Qi Jiaqi Wang 0003 Xiaoyang Wu 0002 Hengshuang Zhao OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detection. 2023 abs/2306.01738 CoRR https://doi.org/10.48550/arXiv.2306.01738 db/journals/corr/corr2306.html#abs-2306-01738

Yunhan Yang Xiaoyang Wu 0002 Tong He 0001 Hengshuang Zhao Xihui Liu SAM3D: Segment Anything in 3D Scenes. 2023 abs/2306.03908 CoRR https://doi.org/10.48550/arXiv.2306.03908 db/journals/corr/corr2306.html#abs-2306-03908

Bohao Peng Zhuotao Tian Xiaoyang Wu 0002 Chengyao Wang Shu Liu 0005 Jingyong Su Jiaya Jia Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstract. 2023 abs/2306.15278 CoRR https://doi.org/10.48550/arXiv.2306.15278 db/journals/corr/corr2306.html#abs-2306-15278

Xiaoyang Wu 0002 Zhuotao Tian Xin Wen 0004 Bohao Peng Xihui Liu Kaicheng Yu Hengshuang Zhao Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. 2023 abs/2308.09718 CoRR https://doi.org/10.48550/arXiv.2308.09718 db/journals/corr/corr2308.html#abs-2308-09718

Zhening Huang Xiaoyang Wu 0002 Xi Chen 0119 Hengshuang Zhao Lei Zhu 0003 Joan Lasenby OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation. 2023 abs/2309.00616 CoRR https://doi.org/10.48550/arXiv.2309.00616 db/journals/corr/corr2309.html#abs-2309-00616

Honghui Yang Sha Zhang 0002 Di Huang Xiaoyang Wu 0002 Haoyi Zhu Tong He 0001 Shixiang Tang Hengshuang Zhao Qibo Qiu Binbin Lin Xiaofei He 0001 Wanli Ouyang UniPAD: A Universal Pre-training Paradigm for Autonomous Driving. 2023 abs/2310.08370 CoRR https://doi.org/10.48550/arXiv.2310.08370 db/journals/corr/corr2310.html#abs-2310-08370

Haoyi Zhu Honghui Yang Xiaoyang Wu 0002 Di Huang Sha Zhang 0002 Xianglong He Tong He 0001 Hengshuang Zhao Chunhua Shen Yu Qiao 0001 Wanli Ouyang PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm. 2023 abs/2310.08586 CoRR https://doi.org/10.48550/arXiv.2310.08586 db/journals/corr/corr2310.html#abs-2310-08586

Zhangyang Qi Ye Fang Zeyi Sun 0002 Xiaoyang Wu 0002 Tong Wu Jiaqi Wang 0003 Dahua Lin Hengshuang Zhao GPT4Point: A Unified Framework for Point-Language Understanding and Generation. 2023 abs/2312.02980 CoRR https://doi.org/10.48550/arXiv.2312.02980 db/journals/corr/corr2312.html#abs-2312-02980

Yunhan Yang Yukun Huang Xiaoyang Wu 0002 Yuan-Chen Guo Song-Hai Zhang Hengshuang Zhao Tong He 0001 Xihui Liu DreamComposer: Controllable 3D Object Generation via Multi-View Conditions. 2023 abs/2312.03611 CoRR https://doi.org/10.48550/arXiv.2312.03611 db/journals/corr/corr2312.html#abs-2312-03611

Xiaoyang Wu 0002 Li Jiang 0009 Peng-Shuai Wang Zhijian Liu Xihui Liu Yu Qiao 0001 Wanli Ouyang Tong He 0001 Hengshuang Zhao Point Transformer V3: Simpler, Faster, Stronger. 2023 abs/2312.10035 CoRR https://doi.org/10.48550/arXiv.2312.10035 db/journals/corr/corr2312.html#abs-2312-10035

Xiaoyang Wu 0002 Yixing Lao Li Jiang 0009 Xihui Liu Hengshuang Zhao Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. 2022 conf/nips/2022 NeurIPS http://papers.nips.cc/paper_files/paper/2022/hash/d78ece6613953f46501b958b7bb4582f-Abstract-Conference.html db/conf/nips/neurips2022.html#0002LJLZ22

Xiaoyang Wu 0002 Yixing Lao Li Jiang 0009 Xihui Liu Hengshuang Zhao Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. 2022 abs/2210.05666 CoRR https://doi.org/10.48550/arXiv.2210.05666 db/journals/corr/corr2210.html#abs-2210-05666

Xiang Bai Xuyang Bai Ioannis K. Brilakis Yan-Pei Cao Chirui Chang Peng Chen Runnan Chen Shuo Chen Xi Chen 0119 Yukang Chen Jiequan Cui Shengliang Deng Daniel DeTone Jakob J. Engel Francis Engelmann Xianzhe Fan Tian Fang Ye Fang Elisabetta Fedele Duncan P. Frost Leonidas J. Guibas Yuanchen GuoYuan-Chen Guo Georgios M. Hadjidemetriou Tong He 0001 Xianglong He Xiaofei He 0001 Di Huang Yukun Huang Zehao Huang Zhening Huang Jiaya Jia Li Jiang 0009 Lingdong Kong Edmund Y. Lam Yixing Lao Joan Lasenby Han Li Shiwei Li 0001 Xin Li 0110 Zhuoling Li Binbin Lin Dahua Lin Or Litany Jiahui Liu 0012 Jianhui Liu Shaoteng Liu Shu Liu 0005 Xiao Liu Xihui Liu Youquan Liu Yu Liu 0063 Zhijian Liu Ziwei Liu 0002 Liangjun Lu Yuxiang Lu Zixin Luo Lan Ma Yuexin Ma Jean-Daniel Nahmias Richard A. Newcombe Khoi Nguyen 0001 Phuc Nguyen Matthias Nießner Wanli Ouyang Liang Pan Bohao Peng Songyou Peng Cuong Pham 0001 Marc Pollefeys Xiaojuan Qi 0001 Zhangyang Qi Yu Qiao 0001 Qibo Qiu Liangliang Ren Jonas Schult Chunhua Shen Tianwei Shen Julian Straub Jingyong Su Zeyi Sun 0002 Ayça Takmaz Shixiang Tang Siyu Tang 0001 Tao Tang Hongbo Tian Zhuotao Tian Federico Tombari Anh Tuan Tran 0001Anh Tran 0001 Yanghai Tsin Johanna Wald Bingwen Wang Chengyao Wang Chenyao Wang Chunjie Wang He Wang Jiaqi Wang 0003 Naiyan Wang Peng-Shuai Wang Shujun Wang Xi Wang 0021 Xin Wen 0004 Tong Wu Christopher XieChris Xie Long Xing Xiang Xu 0009 Xiaogang Xu 0002 Zhenhua Xu 0003 Mi Yan Nuoyuan Yan Xiaosheng Yan Honghui Yang Jinrong Yang Nan Yang Yibo Yang Yunhan Yang Kaicheng Yu Mengchen Zhang 0001 Sha Zhang 0002 Song-Hai Zhang Xiangyu Zhang 0005 Xuanyang Zhang Yuechen Zhang Yujia Zhang 0003 Zhizheng Zhang 0011 Hengshuang Zhao Yong Zhao Fangcheng Zhong Zhisheng Zhong Haoyi Zhu Lei Zhu 0003 Mingkang Zhu