𝗜𝗻𝗳𝗶𝗻𝗶𝗦𝗽𝗹𝗮𝘁: 𝗜𝗺𝗽𝗹𝗶𝗰𝗶𝘁 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗗𝗲𝗰𝗼𝗱𝗶𝗻𝗴 𝗳𝗼𝗿 𝗟𝗮𝗿𝗴𝗲-𝗕𝗮𝘀𝗲𝗹𝗶𝗻𝗲 𝗠𝗼𝗻𝗼𝗰𝘂𝗹𝗮𝗿 𝗩𝗶𝗲𝘄 𝗦𝘆𝗻𝘁𝗵𝗲𝘀𝗶𝘀 Jiawei Wang, Hao Yu, Yongzhen Hu ... Sida Peng arxiv.org/abs/2608.02437 Trending on scholar-inbox.com

𝗛𝘂𝗻𝘆𝘂𝗮𝗻𝟯𝗗-𝗕𝘂𝗳𝗳𝗮𝗹𝗼 𝟭.𝟬: 𝗔 𝗨𝗻𝗶𝗳𝗶𝗲𝗱 𝗠𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗠𝗼𝗱𝗲𝗹 𝗳𝗼𝗿 𝗦𝗰𝗮𝗹𝗮𝗯𝗹𝗲 𝟯𝗗 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻, 𝗨𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗶𝗻𝗴, 𝗮𝗻𝗱 𝗘𝗱𝗶𝘁𝗶𝗻𝗴 Junliang Ye, Kenkun Liu, Guocun Wang ... Chunchao Guo arxiv.org/abs/2608.02711 Trending on scholar-inbox.com

𝗤𝘄𝗲𝗻-𝟯𝗗: 𝗔 𝗚𝗲𝗻𝗲𝗿𝗮𝗹𝗶𝘀𝘁 𝟯𝗗 𝗩𝗶𝘀𝗶𝗼𝗻-𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗠𝗼𝗱𝗲𝗹 𝗳𝗼𝗿 𝗦𝗽𝗮𝘁𝗶𝗮𝗹 𝗨𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗶𝗻𝗴 Lucy Lin, Ayush Jain, Yifan Liu, Katerina Fragkiadaki arxiv.org/abs/2608.02980 Trending on scholar-inbox.com

𝗙𝗶𝗹𝗹𝗚𝗦: 𝗙𝗶𝗹𝗹𝗶𝗻𝗴 𝗢𝗯𝘀𝗲𝗿𝘃𝗮𝘁𝗶𝗼𝗻 𝗚𝗮𝗽𝘀 𝗶𝗻 𝟰𝗗 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗦𝗽𝗹𝗮𝘁𝘁𝗶𝗻𝗴 𝘃𝗶𝗮 𝗩𝗶𝗲𝘄𝗽𝗼𝗶𝗻𝘁-𝗧𝗶𝗺𝗲 𝗦𝗲𝗹𝗲𝗰𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗥𝗲𝗳𝗶𝗻𝗲𝗺𝗲𝗻𝘁 Takashi Otonari, Toshihiko Yamasaki arxiv.org/abs/2607.29284 Trending on scholar-inbox.com

𝗠𝗶𝗻𝗶𝗪𝗼𝗿𝗹𝗱: 𝗗𝗲𝗺𝗼𝗰𝗿𝗮𝘁𝗶𝘇𝗶𝗻𝗴 𝘁𝗵𝗲 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 𝗼𝗳 𝗩𝗶𝗱𝗲𝗼 𝗪𝗼𝗿𝗹𝗱 𝗠𝗼𝗱𝗲𝗹𝘀 𝗳𝗿𝗼𝗺 𝗦𝗰𝗿𝗮𝘁𝗰𝗵 Yian Zhao, Ruochong Zheng, Hongcan Guo ... Jie Chen arxiv.org/abs/2608.01127 Trending on scholar-inbox.com

𝗩𝗶𝗱𝗲𝗼 𝗠𝗼𝗱𝗲𝗹𝘀 𝗮𝘀 𝗡𝗮𝘁𝗶𝘃𝗲 𝟰𝗗 𝗥𝗲𝗻𝗱𝗲𝗿𝗲𝗿𝘀: 𝗪𝗼𝗿𝗹𝗱-𝗚𝗿𝗼𝘂𝗻𝗱𝗲𝗱 𝗖𝗼𝗻𝗱𝗶𝘁𝗶𝗼𝗻𝗶𝗻𝗴 𝗳𝗿𝗼𝗺 𝗔𝗻𝗶𝗺𝗮𝘁𝗲𝗱 𝗠𝗲𝘀𝗵 Junhao Chen, Mingjin Chen, Henghaofan Zhang ... Yufei Li arxiv.org/abs/2608.00094 Trending on scholar-inbox.com

𝗣𝗵𝗶𝗭𝗲𝗿𝗼: 𝗔 𝗪𝗼𝗿𝗹𝗱 𝗠𝗼𝗱𝗲𝗹 𝗕𝘂𝗶𝗹𝘁 𝗔𝗿𝗼𝘂𝗻𝗱 𝗣𝗵𝘆𝘀𝗶𝗰𝗮𝗹 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲 Shuyao Shang, Yuqi Wang, Ruopeng Gao ... Zhaoxiang Zhang arxiv.org/abs/2607.28624 Trending on scholar-inbox.com

𝗔 𝗙𝗿𝗼𝘇𝗲𝗻 𝗣𝗶𝘅𝗲𝗹-𝗦𝗽𝗮𝗰𝗲 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻 𝗠𝗼𝗱𝗲𝗹 𝗖𝗮𝗻 𝗚𝘂𝗶𝗱𝗲 𝗜𝘁𝘀𝗲𝗹𝗳 𝘄𝗶𝘁𝗵 𝗜𝘁𝘀 𝗢𝘄𝗻 𝗦𝗮𝗺𝗽𝗹𝗲𝘀 Zixuan Fu, Chong Wang, Lanqing Guo ... Bihan Wen arxiv.org/abs/2607.29122 Trending on scholar-inbox.com

𝗠𝗲𝘀𝗵𝘆 𝗧𝟮: 𝗙𝗮𝘀𝘁 𝗡𝗮𝘁𝗶𝘃𝗲 𝗠𝗲𝘀𝗵 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝘄𝗶𝘁𝗵 𝗙𝗹𝗼𝘄 𝗠𝗮𝘁𝗰𝗵𝗶𝗻𝗴 Jiale Xu, Rendong Liang, Yuhao Long ... Yuanming Hu arxiv.org/abs/2607.28675 Trending on scholar-inbox.com

𝗖𝗼𝗻𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻𝗮𝗹 𝗡𝗲𝘂𝗿𝗮𝗹 𝗦𝗵𝗮𝗱𝗶𝗻𝗴 𝗳𝗼𝗿 𝗛𝗶𝗴𝗵-𝗤𝘂𝗮𝗹𝗶𝘁𝘆 𝟯𝗗 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 𝗳𝗿𝗼𝗺 𝗠𝘂𝗹𝘁𝗶-𝗩𝗶𝗲𝘄 𝗜𝗺𝗮𝗴𝗲𝘀 Juheon Hwang, Taewan Kim, Heeseok Oh, Jiwoo Kang arxiv.org/abs/2607.28132 Trending on scholar-inbox.com

𝗦𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝗚𝗦: 𝗦𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲-𝗮𝘄𝗮𝗿𝗲 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗦𝗽𝗹𝗮𝘁𝘁𝗶𝗻𝗴 𝗳𝗼𝗿 𝗔𝗿𝘁𝗶𝗰𝘂𝗹𝗮𝘁𝗲𝗱 𝗢𝗯𝗷𝗲𝗰𝘁 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 Gahye Lee, Gyoonseo Kim, Wonjong Jang ... Seungyong Lee arxiv.org/abs/2607.26889 Trending on scholar-inbox.com

𝗠𝗲𝘀𝗵𝗙𝗠: 𝟮𝗗 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀 𝗔𝗿𝗲 𝗔𝗹𝗹 𝗬𝗼𝘂 𝗡𝗲𝗲𝗱 𝗳𝗼𝗿 𝟯𝗗 𝗦𝗵𝗮𝗽𝗲 𝗨𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗶𝗻𝗴 Jinfan Zhou, Richard Liu, Itai Lang, Rana Hanocka arxiv.org/abs/2607.27592 Trending on scholar-inbox.com

𝗚𝗲𝗻𝗶𝗲 𝗦𝗶𝗺 𝗣𝗮𝗻𝗼𝗪𝗼𝗿𝗹𝗱: 𝗔𝗻 𝗜𝗻𝗳𝗶𝗻𝗶𝘁𝗲 𝗜𝗻𝗱𝗼𝗼𝗿 𝟯𝗗 𝗪𝗼𝗿𝗹𝗱 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝗣𝗶𝗽𝗲𝗹𝗶𝗻𝗲 𝘃𝗶𝗮 𝗣𝗮𝗻𝗼𝗿𝗮𝗺𝗶𝗰 𝗦𝗰𝗲𝗻𝗲 𝗠𝗼𝗱𝗲𝗹𝗶𝗻𝗴 𝗮𝗻𝗱 𝗦𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻 Yongxin Su, Linjie Hou, Feng Wang ... Maoqing Yao arxiv.org/abs/2607.26646 Trending on scholar-inbox.com

𝗣𝗮𝗿𝗮𝗹𝗹𝗲𝗹 𝗗𝗲𝗰𝗼𝗱𝗶𝗻𝗴 𝗗𝗶𝘀𝘁𝗶𝗹𝗹𝗮𝘁𝗶𝗼𝗻 𝗳𝗼𝗿 𝗙𝗮𝘀𝘁 𝗜𝗺𝗮𝗴𝗲 𝗮𝗻𝗱 𝗩𝗶𝗱𝗲𝗼 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 Neta Shaul, Chao Liu, Arash Vahdat, Julius Berner arxiv.org/abs/2607.26004 Trending on scholar-inbox.com

𝗩𝗶𝗱𝗠𝗮𝗽: 𝗘𝘅𝗽𝗹𝗼𝗶𝘁𝗶𝗻𝗴 𝗧𝗲𝗺𝗽𝗼𝗿𝗮𝗹 𝗦𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲 𝗳𝗼𝗿 𝗩𝗶𝗱𝗲𝗼-𝗕𝗮𝘀𝗲𝗱 𝗦𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲-𝗳𝗿𝗼𝗺-𝗠𝗼𝘁𝗶𝗼𝗻 Zador Pataki, Paul-Edouard Sarlin, Marc Pollefeys arxiv.org/abs/2607.27194 Trending on scholar-inbox.com

𝗖𝗮𝗺𝗲𝗿𝗮𝗔𝗻𝘆𝘁𝗵𝗶𝗻𝗴: 𝗥𝗲𝗳𝗶𝗹𝗺𝗶𝗻𝗴 𝗩𝗶𝗱𝗲𝗼𝘀 𝘄𝗶𝘁𝗵 𝗔𝗿𝗯𝗶𝘁𝗿𝗮𝗿𝘆 𝗖𝗮𝗺𝗲𝗿𝗮 𝗖𝗼𝗻𝘁𝗿𝗼𝗹 Yixuan Li, Yanhong Zeng, Ka Leong Cheng ... Dahua Lin arxiv.org/abs/2607.24591 Trending on scholar-inbox.com

𝗣𝗶𝗰𝘁𝘂𝗿𝗮: 𝗣𝗲𝗿𝘀𝗽𝗲𝗰𝘁𝗶𝘃𝗲-𝗩𝗶𝗲𝘄 𝗦𝗲𝗹𝗳-𝗣𝗹𝗮𝘆 𝗮𝘁 𝗦𝗰𝗮𝗹𝗲 𝗳𝗼𝗿 𝗗𝗿𝗶𝘃𝗶𝗻𝗴 Yuan Yin, Elias Ramzi, Marc Lafon ... Matthieu Cord arxiv.org/abs/2607.26005 Trending on scholar-inbox.com

𝗪𝗼𝗻𝗱𝗲𝗿: 𝗩𝗶𝗱𝗲𝗼 𝗪𝗼𝗿𝗹𝗱 𝗠𝗼𝗱𝗲𝗹 𝗗𝗼𝗻𝗲 𝗕𝗲𝘁𝘁𝗲𝗿 Jiacong Xu, Hanwen Jiang, Zhixin Shu ... Yiqun Mei arxiv.org/abs/2607.26037 Trending on scholar-inbox.com

𝗩𝗶𝗗𝗦: 𝗩𝗶𝗱𝗲𝗼 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻 𝗦𝗵𝗮𝗱𝗲𝗿 𝘂𝘀𝗶𝗻𝗴 𝟯𝗗 𝗙𝗮𝗰𝗲 𝗧𝗿𝗮𝗰𝗸𝗶𝗻𝗴 Wenbo Ji, Davide Davoli, Zhe Chen ... Jiapeng Tang arxiv.org/abs/2607.24124 Trending on scholar-inbox.com

𝗨𝗻𝗶𝗚𝗲𝗻-𝗔𝗥: 𝗨𝗻𝗶𝗳𝘆𝗶𝗻𝗴 𝗩𝗶𝘀𝘂𝗮𝗹 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝘄𝗶𝘁𝗵 𝗔𝘂𝘁𝗼-𝗥𝗲𝗴𝗿𝗲𝘀𝘀𝗶𝘃𝗲 𝗠𝗼𝗱𝗲𝗹𝗶𝗻𝗴 Zhipeng Bao, Zhen Zhu, Nupur Kumari ... Martial Hebert arxiv.org/abs/2607.24157 Trending on scholar-inbox.com

𝗖𝗹𝗼𝘀𝗶𝗻𝗴 𝘁𝗵𝗲 𝗟𝗼𝗼𝗽: 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴-𝗙𝗿𝗲𝗲 𝗥𝗲𝘃𝗶𝘀𝗶𝘁 𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆 𝗳𝗼𝗿 𝗔𝘂𝘁𝗼𝗿𝗲𝗴𝗿𝗲𝘀𝘀𝗶𝘃𝗲 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗥𝗲𝗻𝗱𝗲𝗿𝗶𝗻𝗴 Wenchao Ma, Changran Liu, Sharon X. Huang, Haomiao Jiang arxiv.org/abs/2607.21848 Trending on scholar-inbox.com

𝟯𝗗-𝗔𝘄𝗮𝗿𝗲 𝗩𝗟𝗠𝘀 𝘄𝗶𝘁𝗵 𝗜𝗺𝗽𝗹𝗶𝗰𝗶𝘁 𝗮𝗻𝗱 𝗘𝘅𝗽𝗹𝗶𝗰𝗶𝘁 𝗚𝗲𝗼𝗺𝗲𝘁𝗿𝗶𝗲𝘀 Wenhao Li, Xueying Jiang, Quanhao Qian ... Gongjie Zhang arxiv.org/abs/2607.21595 Trending on scholar-inbox.com

𝗗𝗲𝗳𝗼𝗿𝗺𝗮𝗯𝗹𝗲 𝗧𝗿𝗶𝗮𝗻𝗴𝗹𝗲 𝗦𝗽𝗹𝗮𝘁𝘁𝗶𝗻𝗴: 𝗙𝗹𝗲𝘅𝗶𝗯𝗹𝗲 𝗣𝗿𝗶𝗺𝗶𝘁𝗶𝘃𝗲𝘀 𝗳𝗼𝗿 𝗥𝗲𝗮𝗹-𝗧𝗶𝗺𝗲 𝗥𝗮𝗱𝗶𝗮𝗻𝗰𝗲 𝗙𝗶𝗲𝗹𝗱 𝗥𝗲𝗻𝗱𝗲𝗿𝗶𝗻𝗴 Oriol Jiménez-Ayguadé, Antonio Agudo arxiv.org/abs/2607.22446 Trending on scholar-inbox.com

𝗦𝗠𝟰𝗥𝗧: 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗦𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝗱 𝗠𝗼𝘁𝗶𝗼𝗻 𝗚𝗲𝗼𝗺𝗲𝘁𝗿𝘆 𝗳𝗼𝗿 𝟰𝗗 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 Shing Ho J. Lin, Wenzhao Zheng, Dong Zhuo ... Jiwen Lu arxiv.org/abs/2607.22534 Trending on scholar-inbox.com

𝟯𝗗-𝗚𝗜𝗠𝗣: 𝗪𝗵𝗲𝗻 𝟯𝗗 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗜𝗻𝗽𝗮𝗶𝗻𝘁𝗶𝗻𝗴 𝗠𝗲𝗲𝘁𝘀 𝗣𝗮𝘁𝗰𝗵𝗠𝗮𝘁𝗰𝗵 Xuening Tian, Dieter Schmalstieg, Shohei Mori arxiv.org/abs/2607.20789 Trending on scholar-inbox.com

𝗔𝘅𝗼𝗹𝗼𝘁𝗹𝟯𝗗: 𝗮 𝗨𝗻𝗶𝗳𝗶𝗲𝗱 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸 𝗳𝗼𝗿 𝗙𝗮𝗶𝘁𝗵𝗳𝘂𝗹 𝟯𝗗 𝗦𝗵𝗮𝗽𝗲 𝗖𝗼𝗺𝗽𝗹𝗲𝘁𝗶𝗼𝗻 Anita Hu, Maria Shugrina arxiv.org/abs/2607.20660 Trending on scholar-inbox.com

𝗦𝗲𝗹𝗳-𝗦𝘂𝗽𝗲𝗿𝘃𝗶𝘀𝗲𝗱 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗼𝗳 𝗦𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝗱 𝗗𝘆𝗻𝗮𝗺𝗶𝗰𝘀 𝗳𝗿𝗼𝗺 𝗩𝗶𝗱𝗲𝗼𝘀 Lukas Knobel, Andrew Zisserman, Yuki M. Asano arxiv.org/abs/2607.21576 Trending on scholar-inbox.com

𝗗𝘂𝗦𝗣𝗶𝗧: 𝗗𝘂𝗮𝗹-𝗕𝗿𝗮𝗻𝗰𝗵 𝗦𝘂𝗯-𝗣𝗮𝘁𝗰𝗵 𝗣𝗶𝘅𝗲𝗹 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿 Yunpeng Bai, Yossi Gandelsman, Michaël Gharbi arxiv.org/abs/2607.18510 Trending on scholar-inbox.com

𝗔𝗧𝗦𝗽𝗹𝗮𝘁: 𝗖𝗼𝗺𝗽𝗮𝗰𝘁 𝗙𝗲𝗲𝗱-𝗳𝗼𝗿𝘄𝗮𝗿𝗱 𝟯𝗗 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗦𝗽𝗹𝗮𝘁𝘁𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗔𝗱𝗮𝗽𝘁𝗶𝘃𝗲 𝗧𝗼𝗸𝗲𝗻 𝗘𝘅𝗽𝗮𝗻𝘀𝗶𝗼𝗻 Cho In, Jeonghwan Cho, Mijin Yoo ... Seon Joo Kim arxiv.org/abs/2607.20417 Trending on scholar-inbox.com

𝗔𝗻𝗶𝗚𝗦: 𝗕𝗿𝗶𝗱𝗴𝗶𝗻𝗴 𝗥𝗲𝗻𝗱𝗲𝗿𝗶𝗻𝗴 𝗮𝗻𝗱 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻 𝗣𝗿𝗶𝗼𝗿 𝗳𝗼𝗿 𝟯𝗗 𝗦𝗰𝗲𝗻𝗲 𝗔𝗻𝗶𝗺𝗮𝘁𝗶𝗼𝗻 Yen-Chi Cheng, Chen Gao, Chuhan Chen ... Hung-Yu Tseng arxiv.org/abs/2607.18539 Trending on scholar-inbox.com