𝗚𝗿𝗼𝘂𝗻𝗱𝗲𝗱-𝗘𝘅𝗼𝟮𝗘𝗴𝗼: 𝗦𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝗱 𝗦𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝗚𝗿𝗼𝘂𝗻𝗱𝗶𝗻𝗴 𝗳𝗼𝗿 𝗥𝗼𝗯𝘂𝘀𝘁 𝗘𝘅𝗼𝗰𝗲𝗻𝘁𝗿𝗶𝗰-𝘁𝗼-𝗘𝗴𝗼𝗰𝗲𝗻𝘁𝗿𝗶𝗰 𝗩𝗶𝗱𝗲𝗼 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 Shengze Wang, Michael Stengel, Tianye Li ... Shalini De Mello arxiv.org/abs/2608.20534 Trending on scholar-inbox.com

𝗠𝘂𝗹𝘁𝗶𝗖𝘂𝗯𝗲: 𝗖𝗼𝗺𝗽𝗼𝘀𝗶𝘁𝗶𝗼𝗻𝗮𝗹 𝟯𝗗 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝗪𝗶𝘁𝗵 𝗣𝗮𝗿𝘁-𝗟𝗲𝘃𝗲𝗹 𝗦𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝗮𝗻𝗱 𝗦𝗽𝗮𝘁𝗶𝗮𝗹 𝗖𝗼𝗻𝘁𝗿𝗼𝗹 Ava Pun, Kangle Deng, Yiheng Zhu ... Tinghui Zhou arxiv.org/abs/2608.20448 Trending on scholar-inbox.com

𝗙𝗶𝘅𝗔𝗻𝘆𝘁𝗵𝗶𝗻𝗴: 𝟯𝗗-𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝘁 𝗥𝗲𝗻𝗱𝗲𝗿𝗶𝗻𝗴 𝗥𝗲𝗳𝗶𝗻𝗲𝗺𝗲𝗻𝘁 𝘃𝗶𝗮 𝗩𝗶𝗱𝗲𝗼 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗣𝗿𝗶𝗼𝗿𝘀 Khiem Vuong, Deva Ramanan, Srinivasa Narasimhan arxiv.org/abs/2608.23549 Trending on scholar-inbox.com

𝗨𝗻𝗶𝗳𝗶𝗲𝗱 𝗮𝗻𝗱 𝗘𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗣𝗼𝗶𝗻𝘁-𝗟𝗶𝗻𝗲 𝗟𝗼𝗰𝗮𝗹 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀 François Costa, Raphael Kreft, Eckhard Goedeke ... Marc Pollefeys arxiv.org/abs/2608.19894 Trending on scholar-inbox.com

𝗧𝗼𝗽𝗼𝗦𝘂𝗿𝗳𝗲𝗹: 𝗖𝗹𝗼𝘀𝗶𝗻𝗴 𝘁𝗵𝗲 𝗟𝗼𝗼𝗽 𝗯𝗲𝘁𝘄𝗲𝗲𝗻 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗦𝘂𝗿𝗳𝗲𝗹𝘀 𝗮𝗻𝗱 𝗠𝗲𝘀𝗵𝗲𝘀 𝗳𝗼𝗿 𝗦𝘂𝗿𝗳𝗮𝗰𝗲 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 Chuanjin Fan, Wenjie Chang, Bohao Liao ... Tianzhu Zhang arxiv.org/abs/2608.20687 Trending on scholar-inbox.com

𝗦𝘁𝗿𝗲𝗮𝗺𝟯𝗗𝘃𝟮: 𝗚𝗲𝗼𝗺𝗲𝘁𝗿𝗶𝗰-𝗦𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝗙𝘂𝘀𝗶𝗼𝗻 𝗘𝗻𝗵𝗮𝗻𝗰𝗲𝗱 𝗦𝘁𝗿𝗲𝗮𝗺𝗶𝗻𝗴 𝗭𝗲𝗿𝗼-𝗦𝗵𝗼𝘁 𝟯𝗗 𝗦𝗰𝗲𝗻𝗲 𝗨𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗶𝗻𝗴 Jie Xu, Na Zhao arxiv.org/abs/2608.21136 Trending on scholar-inbox.com

𝗗𝗿𝗲𝗮𝗺𝗛𝗮𝗻𝗱: 𝗥𝗲𝗽𝘂𝗿𝗽𝗼𝘀𝗶𝗻𝗴 𝗩𝗶𝗱𝗲𝗼 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻 𝗠𝗼𝗱𝗲𝗹𝘀 𝗳𝗼𝗿 𝗢𝗰𝗰𝗹𝘂𝘀𝗶𝗼𝗻-𝗥𝗼𝗯𝘂𝘀𝘁 𝗘𝗴𝗼𝗰𝗲𝗻𝘁𝗿𝗶𝗰 𝟯𝗗 𝗛𝗮𝗻𝗱 𝗠𝗼𝘁𝗶𝗼𝗻 𝗥𝗲𝗰𝗼𝘃𝗲𝗿𝘆 Yufei Liu, Xixi Wang, Hao Li ... Hongsheng Li arxiv.org/abs/2608.20308 Trending on scholar-inbox.com

𝗕𝗹𝗼𝗰𝗸𝟯𝗗: 𝗘𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗧𝗲𝘅𝘁-𝘁𝗼-𝟯𝗗 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝘃𝗶𝗮 𝗕𝗹𝗼𝗰𝗸-𝗪𝗶𝘀𝗲 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻 Bowen Cui, Weijie Wang, Zeyu Zhang ... Bohan Zhuang arxiv.org/abs/2608.19567 Trending on scholar-inbox.com

𝟰𝗗𝗔𝗻𝘆𝗼𝗻𝗲: 𝗖𝗿𝗲𝗮𝘁𝗲 𝗔𝗻𝘆𝗼𝗻𝗲 𝗶𝗻 𝟰𝗗 𝗳𝗿𝗼𝗺 𝗮 𝗖𝗮𝘀𝘂𝗮𝗹 𝗠𝗼𝗻𝗼𝗰𝘂𝗹𝗮𝗿 𝗩𝗶𝗱𝗲𝗼 Yudong Jin, Tao Xie, Qihang Zhang ... Yinghao Xu arxiv.org/abs/2608.20335 Trending on scholar-inbox.com

𝗥𝗔𝗗𝗺𝗲𝘀𝗵: 𝗥𝗲𝗺𝗲𝘀𝗵-𝗔𝘄𝗮𝗿𝗲 𝗠𝗲𝘀𝗵 𝗗𝗲𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻 Nam Anh Dinh, Itai Lang, Oded Stein, Rana Hanocka arxiv.org/abs/2608.17182 Trending on scholar-inbox.com

𝗟𝘂𝗺𝗶𝗧𝗼𝗸𝗲𝗻𝘀: 𝟯𝗗 𝗥𝗲𝗹𝗶𝗴𝗵𝘁𝗶𝗻𝗴 𝘃𝗶𝗮 𝗧𝗼𝗸𝗲𝗻-𝗦𝗽𝗮𝗰𝗲 𝗟𝗶𝗴𝗵𝘁𝗶𝗻𝗴 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻 Yiwen Chen, Matheus Gadelha, Huaizu Jiang arxiv.org/abs/2608.18215 Trending on scholar-inbox.com

𝗗𝗲𝗽𝘁𝗵 𝗔𝗻𝘆𝘁𝗵𝗶𝗻𝗴 𝗩𝟰: 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝟰𝗗 𝗦𝗰𝗲𝗻𝗲 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 𝘃𝗶𝗮 𝗥𝗶𝗲𝗺𝗮𝗻𝗻𝗶𝗮𝗻 𝗙𝗹𝗼𝘄 𝗠𝗮𝘁𝗰𝗵𝗶𝗻𝗴 𝗼𝗻 𝟰𝗗 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗦𝗽𝗹𝗮𝘁𝘁𝗶𝗻𝗴 Jiaming Fan, Jian Lu, Jinling Jia, Chenbin Zhang arxiv.org/abs/2608.18388 Trending on scholar-inbox.com

𝗨𝗻𝗶𝗤𝘂𝗲𝗿𝘆𝟰𝗥: 𝗨𝗻𝗶𝗳𝗶𝗲𝗱 𝟰𝗗 𝗦𝗰𝗲𝗻𝗲 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 𝗳𝗿𝗼𝗺 𝗮 𝗦𝗶𝗻𝗴𝗹𝗲 𝗤𝘂𝗲𝗿𝘆 Tiancheng Chen, Sheng Tang, Wenhua Jin ... Zesong Li arxiv.org/abs/2608.17283 Trending on scholar-inbox.com

𝗗𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝘁𝗶𝗮𝗯𝗹𝗲 𝗩𝗼𝗿𝗼𝗻𝗼𝗶 𝗥𝗮𝘆 𝗧𝗿𝗮𝗰𝗶𝗻𝗴 𝗕𝗲𝘆𝗼𝗻𝗱 𝗥𝗮𝘀𝘁𝗲𝗿𝗶𝘇𝗮𝘁𝗶𝗼𝗻 𝗦𝗽𝗲𝗲𝗱𝘀 Bernardo Taveira, Carl Lindström, Joakim Johnander, Fredrik Kahl arxiv.org/abs/2608.17682 Trending on scholar-inbox.com

𝗚𝗲𝗻𝗥𝗲𝗰: 𝗞𝗻𝗼𝘄𝗶𝗻𝗴 𝗪𝗵𝗲𝗿𝗲 𝘁𝗼 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁 𝗮𝗻𝗱 𝗪𝗵𝗲𝗿𝗲 𝘁𝗼 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗲 Ata Çelen, Jaewoo Jung, Federico Tombari ... Daniel Barath arxiv.org/abs/2608.17832 Trending on scholar-inbox.com

𝗔𝗻 𝗘𝗺𝗽𝗶𝗿𝗶𝗰𝗮𝗹 𝗦𝘁𝘂𝗱𝘆 𝗼𝗳 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 𝗣𝗶𝘅𝗲𝗹-𝗦𝗽𝗮𝗰𝗲 𝗧𝗲𝘅𝘁-𝘁𝗼-𝗜𝗺𝗮𝗴𝗲 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻 𝗠𝗼𝗱𝗲𝗹𝘀 Dengyang Jiang, Ruoyi Du, Zhennan Chen ... Steven Hoi arxiv.org/abs/2608.16887 Trending on scholar-inbox.com

𝗕𝗲𝘆𝗼𝗻𝗱 𝗧𝗲𝘅𝘁 𝗖𝗼𝗻𝗱𝗶𝘁𝗶𝗼𝗻𝗶𝗻𝗴: 𝗔 𝗦𝘆𝘀𝘁𝗲𝗺𝗮𝘁𝗶𝗰 𝗦𝘁𝘂𝗱𝘆 𝗼𝗳 𝗠𝗟𝗟𝗠-𝗗𝗶𝗧 𝗙𝘂𝘀𝗶𝗼𝗻 𝗳𝗼𝗿 𝗩𝗶𝗱𝗲𝗼 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 Yanbo Ding, Yijia Fan, Caihua Shan ... Yali Wang arxiv.org/abs/2608.14043 Trending on scholar-inbox.com

𝗦𝗽𝗹𝗮𝘁𝗚𝘂𝗶𝗱𝗲: 𝗚𝗲𝗼𝗺𝗲𝘁𝗿𝗶𝗰 𝗣𝗿𝗶𝗼𝗿𝘀 𝗳𝗿𝗼𝗺 𝟯𝗗 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻𝘀 𝗳𝗼𝗿 𝗣𝗼𝘀𝗲-𝗙𝗿𝗲𝗲 𝗡𝗼𝘃𝗲𝗹 𝗩𝗶𝗲𝘄 𝗦𝘆𝗻𝘁𝗵𝗲𝘀𝗶𝘀 Yejun Zhang, Zihan Wang, Xu Ji ... Juho Kannala arxiv.org/abs/2608.16863 Trending on scholar-inbox.com

𝗟𝗼𝗰𝘂𝘀𝗚𝗦: 𝗦𝗽𝗮𝘁𝗶𝗮𝗹𝗹𝘆 𝗚𝗿𝗼𝘂𝗻𝗱𝗲𝗱 𝗧𝗼𝗸𝗲𝗻𝘀 𝗳𝗼𝗿 𝗙𝗲𝗲𝗱-𝗙𝗼𝗿𝘄𝗮𝗿𝗱 𝟯𝗗 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗦𝗽𝗹𝗮𝘁𝘁𝗶𝗻𝗴 Wenyu Li, Sidun Liu, Tongrui Hu ... Yong Dou arxiv.org/abs/2608.12825 Trending on scholar-inbox.com

𝗥𝗚𝗕𝗫-𝗡𝗲𝘅𝘁: 𝗧𝗼𝘄𝗮𝗿𝗱𝘀 𝗥𝗲𝗮𝗹𝗶𝘀𝘁𝗶𝗰 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗥𝗲𝗻𝗱𝗲𝗿𝗶𝗻𝗴 𝗳𝗿𝗼𝗺 𝗚-𝗕𝘂𝗳𝗳𝗲𝗿𝘀 Zheng Zeng, Marco Salvi, Lifan Wu ... Miloš Hašan arxiv.org/abs/2608.13929 Trending on scholar-inbox.com

𝗠𝗮𝗿𝗶𝗼𝗻𝗲𝘁𝘁𝗲: 𝗣𝗿𝗲𝗱𝗶𝗰𝘁𝗶𝗻𝗴 𝗪𝗼𝗿𝗹𝗱 𝗦𝘁𝗮𝘁𝗲𝘀, 𝗥𝗲𝗻𝗱𝗲𝗿𝗶𝗻𝗴 𝗚𝗲𝗼𝗺𝗲𝘁𝗿𝘆, 𝗣𝗮𝗶𝗻𝘁𝗶𝗻𝗴 𝗔𝗽𝗽𝗲𝗮𝗿𝗮𝗻𝗰𝗲 Zian Meng, Zhen Li, Chuanhao Li ... Kaipeng Zhang arxiv.org/abs/2608.14530 Trending on scholar-inbox.com

𝗚𝗲𝗼𝗺𝗲𝘁𝗿𝘆-𝗚𝗿𝗼𝘂𝗻𝗱𝗲𝗱 𝗨𝗻𝗶𝗳𝗶𝗲𝗱 𝟯𝗗 𝗣𝗲𝗿𝗰𝗲𝗽𝘁𝗶𝗼𝗻 𝗳𝗼𝗿 𝗔𝘂𝘁𝗼𝗻𝗼𝗺𝗼𝘂𝘀 𝗗𝗿𝗶𝘃𝗶𝗻𝗴 Longfei Xu, Xiaohui Wang, Zehao Huang ... Si Liu arxiv.org/abs/2608.13147 Trending on scholar-inbox.com

𝗗𝗿𝗲𝗮𝗺𝗫-𝗣𝗵𝗶 𝟭.𝟬: 𝗔𝗰𝘁𝗶𝗼𝗻-𝗖𝗼𝗻𝗱𝗶𝘁𝗶𝗼𝗻𝗲𝗱 𝗩𝗶𝗱𝗲𝗼 𝗪𝗼𝗿𝗹𝗱 𝗠𝗼𝗱𝗲𝗹 𝗳𝗼𝗿 𝗥𝗼𝗯𝗼𝘁𝗶𝗰 𝗠𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗶𝗼𝗻 DreamX Team, Rui Chen, Xiangxiang Chu ... Pengfei Zhang arxiv.org/abs/2608.13489 Trending on scholar-inbox.com

𝗩-𝗥𝗔𝗘: 𝗥𝗲𝘁𝗵𝗶𝗻𝗸𝗶𝗻𝗴 𝗩𝗶𝗱𝗲𝗼 𝗟𝗮𝘁𝗲𝗻𝘁 𝗦𝗽𝗮𝗰𝗲𝘀 𝗳𝗼𝗿 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 Minghui Guo, Shengqiong Wu, Hao Fei arxiv.org/abs/2608.13556 Trending on scholar-inbox.com

𝗟𝗘𝗚𝗢: 𝗟𝗲𝘃𝗲𝗹𝗲𝗱 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗦𝗽𝗹𝗮𝘁𝘁𝗶𝗻𝗴 Yuning Peng, Haiping Wang, Yuan Liu ... Bisheng Yang arxiv.org/abs/2608.10057 Trending on scholar-inbox.com

𝗦𝘁𝗿𝗲𝗮𝗺 𝗙𝗼𝗿𝗰𝗶𝗻𝗴: 𝗖𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗻𝗴 𝗨𝗻𝗶𝗳𝗶𝗲𝗱 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 𝗧𝗿𝗮𝗷𝗲𝗰𝘁𝗼𝗿𝘆 𝗳𝗼𝗿 𝗥𝗼𝗯𝘂𝘀𝘁 𝗦𝘁𝗿𝗲𝗮𝗺𝗶𝗻𝗴 𝗩𝗶𝗱𝗲𝗼 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 Yueting Zhu, Yuehao Song, Kaicheng Zhang ... Xinggang Wang arxiv.org/abs/2608.10439 Trending on scholar-inbox.com

𝗟𝗶𝘃𝗲𝗔𝗻𝗶𝗺𝗮𝘁𝗲: 𝗦𝘁𝗮𝗯𝗹𝗲 𝗟𝗼𝗻𝗴-𝗙𝗼𝗿𝗺 𝗦𝘁𝗿𝗲𝗮𝗺𝗶𝗻𝗴 𝗛𝘂𝗺𝗮𝗻 𝗔𝗻𝗶𝗺𝗮𝘁𝗶𝗼𝗻 𝗶𝗻 𝗥𝗲𝗮𝗹-𝗧𝗶𝗺𝗲 Yuxuan Zhang, Haozhong Xiong, Yubo Huang ... Liwei Wang arxiv.org/abs/2608.11745 Trending on scholar-inbox.com

𝗦𝗲𝗹𝗳-𝗚𝗲𝗼𝗺𝗲𝘁𝗿𝘆: 𝗚𝗧-𝗙𝗿𝗲𝗲 𝗮𝗻𝗱 𝗣𝗹𝘂𝗴-𝗮𝗻𝗱-𝗣𝗹𝗮𝘆 𝗧𝗲𝘀𝘁-𝗧𝗶𝗺𝗲 𝗔𝗱𝗮𝗽𝘁𝗮𝘁𝗶𝗼𝗻 𝗳𝗼𝗿 𝗚𝗲𝗼𝗺𝗲𝘁𝗿𝗶𝗰𝗮𝗹𝗹𝘆 𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝘁 𝟯𝗗 𝗩𝗶𝘀𝗶𝗼𝗻 𝗙𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗠𝗼𝗱𝗲𝗹𝘀 Seokhyun Youn, Dahyeon Kye, Sung-Ho Bae, Jihyong Oh arxiv.org/abs/2608.10708 Trending on scholar-inbox.com

𝗕𝗲𝘆𝗼𝗻𝗱 𝗣𝗶𝘅𝗲𝗹𝘀: 𝗙𝗿𝗼𝗺 𝗩𝗶𝗱𝗲𝗼 𝗣𝗿𝗶𝗼𝗿𝘀 𝘁𝗼 𝟰𝗗 𝗪𝗼𝗿𝗹𝗱𝘀 Zihao Liu, Xiaolong Shen, Zhenglin Zhou ... Yi Yang arxiv.org/abs/2608.10744 Trending on scholar-inbox.com

𝗧𝗵𝗿𝗲𝗲 𝗡𝗲𝗰𝗲𝘀𝘀𝗮𝗿𝘆 𝗣𝗿𝗶𝗻𝗰𝗶𝗽𝗹𝗲𝘀 𝗳𝗼𝗿 𝗦𝗲𝗹𝗳-𝗦𝘂𝗽𝗲𝗿𝘃𝗶𝘀𝗲𝗱 𝗩𝗶𝘀𝘂𝗮𝗹 𝗥𝗲𝗽𝗿𝗲𝘀𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 Nikos Giakoumoglou, Paschalis Giakoumoglou, Tania Stathaki arxiv.org/abs/2608.08309 Trending on scholar-inbox.com