Lightnews — Scholar-powered news

Vision and Graphics Trends @si-cv-graphics.bsky.social · 5m

𝗦𝗵𝗮𝗽𝗲𝗚𝗲𝗻𝟰𝗗: 𝗧𝗼𝘄𝗮𝗿𝗱𝘀 𝗛𝗶𝗴𝗵 𝗤𝘂𝗮𝗹𝗶𝘁𝘆 𝟰𝗗 𝗦𝗵𝗮𝗽𝗲 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝗳𝗿𝗼𝗺 𝗩𝗶𝗱𝗲𝗼𝘀
Jiraphon Yenphraphai, Ashkan Mirzaei, Jianqi Chen ... Chaoyang Wang
arxiv.org/abs/2510.06208
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 5m

𝗛𝗼𝗹𝗼𝗦𝗰𝗲𝗻𝗲: 𝗦𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻-𝗥𝗲𝗮𝗱𝘆 𝗜𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝘃𝗲 𝟯𝗗 𝗪𝗼𝗿𝗹𝗱𝘀 𝗳𝗿𝗼𝗺 𝗮 𝗦𝗶𝗻𝗴𝗹𝗲 𝗩𝗶𝗱𝗲𝗼
Hongchi Xia, Chih-Hao Lin, Hao-Yu Hsu ... Shenlong Wang
arxiv.org/abs/2510.05560
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 5m

𝗛𝘂𝗺𝗮𝗻𝟯𝗥: 𝗘𝘃𝗲𝗿𝘆𝗼𝗻𝗲 𝗘𝘃𝗲𝗿𝘆𝘄𝗵𝗲𝗿𝗲 𝗔𝗹𝗹 𝗮𝘁 𝗢𝗻𝗰𝗲
Yue Chen, Xingyu Chen, Yuxuan Xue ... Gerard Pons-Moll
arxiv.org/abs/2510.06219
Trending on www.scholar-inbox.com

1

Vision and Graphics Trends @si-cv-graphics.bsky.social · 1d

𝗦𝗰𝗮𝗹𝗶𝗻𝗴 𝗦𝗲𝗾𝘂𝗲𝗻𝗰𝗲-𝘁𝗼-𝗦𝗲𝗾𝘂𝗲𝗻𝗰𝗲 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗡𝗲𝘂𝗿𝗮𝗹 𝗥𝗲𝗻𝗱𝗲𝗿𝗶𝗻𝗴
Shikun Liu, Kam Woh Ng, Wonbong Jang ... Juan-Manuel Pérez-Rúa
arxiv.org/abs/2510.04236
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 1d

𝗩𝗶𝘀𝘂𝗮𝗹 𝗢𝗱𝗼𝗺𝗲𝘁𝗿𝘆 𝘄𝗶𝘁𝗵 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿𝘀
Vlardimir Yugay, Duy-Kien Nguyen, Theo Gevers ... Martin R. Oswald
arxiv.org/abs/2510.03348
Trending on www.scholar-inbox.com

2

Vision and Graphics Trends @si-cv-graphics.bsky.social · 1d

𝗨𝗻𝗶𝘃𝗲𝗿𝘀𝗮𝗹 𝗕𝗲𝘁𝗮 𝗦𝗽𝗹𝗮𝘁𝘁𝗶𝗻𝗴
Rong Liu, Zhongpai Gao, Benjamin Planche ... Ziyan Wu
arxiv.org/abs/2510.03312
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 2d

𝗣𝗵𝘆𝘀𝗛𝗠𝗥: 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗛𝘂𝗺𝗮𝗻𝗼𝗶𝗱 𝗖𝗼𝗻𝘁𝗿𝗼𝗹 𝗣𝗼𝗹𝗶𝗰𝗶𝗲𝘀 𝗳𝗿𝗼𝗺 𝗩𝗶𝘀𝗶𝗼𝗻 𝗳𝗼𝗿 𝗣𝗵𝘆𝘀𝗶𝗰𝗮𝗹𝗹𝘆 𝗣𝗹𝗮𝘂𝘀𝗶𝗯𝗹𝗲 𝗛𝘂𝗺𝗮𝗻 𝗠𝗼𝘁𝗶𝗼𝗻 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻
Qiao Feng, Yiming Huang, Yufu Wang ... Lingjie Liu
arxiv.org/abs/2510.02566
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 2d

𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝘁𝗼 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗲 𝗢𝗯𝗷𝗲𝗰𝘁 𝗜𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻𝘀 𝘄𝗶𝘁𝗵 𝗣𝗵𝘆𝘀𝗶𝗰𝘀-𝗚𝘂𝗶𝗱𝗲𝗱 𝗩𝗶𝗱𝗲𝗼 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻
David Romero, Ariana Bermudez, Hao Li ... Ivan Laptev
arxiv.org/abs/2510.02284
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 2d

𝗙𝗦𝗙𝗦𝗽𝗹𝗮𝘁𝘁𝗲𝗿: 𝗕𝘂𝗶𝗹𝗱 𝗦𝘂𝗿𝗳𝗮𝗰𝗲 𝗮𝗻𝗱 𝗡𝗼𝘃𝗲𝗹 𝗩𝗶𝗲𝘄𝘀 𝘄𝗶𝘁𝗵 𝗦𝗽𝗮𝗿𝘀𝗲-𝗩𝗶𝗲𝘄𝘀 𝘄𝗶𝘁𝗵𝗶𝗻 𝟯𝗺𝗶𝗻
Yibin Zhao, Yihan Pan, Jun Nan, Jianjun Yi
arxiv.org/abs/2510.02691
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 3d

𝗖𝗮𝗻 𝗪𝗼𝗿𝗹𝗱 𝗠𝗼𝗱𝗲𝗹𝘀 𝗕𝗲𝗻𝗲𝗳𝗶𝘁 𝗩𝗟𝗠𝘀 𝗳𝗼𝗿 𝗪𝗼𝗿𝗹𝗱 𝗗𝘆𝗻𝗮𝗺𝗶𝗰𝘀?
Kevin Zhang, Kuangzhi Ge, Xiaowei Chi ... Shanghang Zhang
arxiv.org/abs/2510.00855
Trending on www.scholar-inbox.com

1

Vision and Graphics Trends @si-cv-graphics.bsky.social · 3d

𝗦𝗲𝗹𝗳-𝗙𝗼𝗿𝗰𝗶𝗻𝗴++: 𝗧𝗼𝘄𝗮𝗿𝗱𝘀 𝗠𝗶𝗻𝘂𝘁𝗲-𝗦𝗰𝗮𝗹𝗲 𝗛𝗶𝗴𝗵-𝗤𝘂𝗮𝗹𝗶𝘁𝘆 𝗩𝗶𝗱𝗲𝗼 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻
Justin Cui, Jie Wu, Ming Li ... Cho-Jui Hsieh
arxiv.org/abs/2510.02283
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 3d

𝗨𝗻𝗶𝗩𝗲𝗿𝘀𝗲: 𝗨𝗻𝗹𝗲𝗮𝘀𝗵𝗶𝗻𝗴 𝘁𝗵𝗲 𝗦𝗰𝗲𝗻𝗲 𝗣𝗿𝗶𝗼𝗿 𝗼𝗳 𝗩𝗶𝗱𝗲𝗼 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻 𝗠𝗼𝗱𝗲𝗹𝘀 𝗳𝗼𝗿 𝗥𝗼𝗯𝘂𝘀𝘁 𝗥𝗮𝗱𝗶𝗮𝗻𝗰𝗲 𝗙𝗶𝗲𝗹𝗱 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻
Jin Cao, Hongrui Wu, Ziyong Feng ... Sida Peng
arxiv.org/abs/2510.01669
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 6d

𝗣𝗔𝗗𝟯𝗥: 𝗣𝗼𝘀𝗲-𝗔𝘄𝗮𝗿𝗲 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝟯𝗗 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 𝗳𝗿𝗼𝗺 𝗖𝗮𝘀𝘂𝗮𝗹 𝗩𝗶𝗱𝗲𝗼𝘀
Ting-Hsuan Liao, Haowen Liu, Yiran Xu ... Jia-Bin Huang
arxiv.org/abs/2509.25183
Trending on www.scholar-inbox.com

1 1

Vision and Graphics Trends @si-cv-graphics.bsky.social · 6d

𝗔 𝗦𝗰𝗲𝗻𝗲 𝗶𝘀 𝗪𝗼𝗿𝘁𝗵 𝗮 𝗧𝗵𝗼𝘂𝘀𝗮𝗻𝗱 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀: 𝗙𝗲𝗲𝗱-𝗙𝗼𝗿𝘄𝗮𝗿𝗱 𝗖𝗮𝗺𝗲𝗿𝗮 𝗟𝗼𝗰𝗮𝗹𝗶𝘇𝗮𝘁𝗶𝗼𝗻 𝗳𝗿𝗼𝗺 𝗮 𝗖𝗼𝗹𝗹𝗲𝗰𝘁𝗶𝗼𝗻 𝗼𝗳 𝗜𝗺𝗮𝗴𝗲 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀
Axel Barroso-Laguna, Tommaso Cavallari, Victor Adrian Prisacariu, Eric Brachmann
arxiv.org/abs/2510.00978
Trending on www.scholar-inbox.com

1

Vision and Graphics Trends @si-cv-graphics.bsky.social · 6d

𝗜𝗻𝘀𝘁𝗮𝗻𝘁𝟰𝗗: 𝟰𝗗 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗦𝗽𝗹𝗮𝘁𝘁𝗶𝗻𝗴 𝗶𝗻 𝗠𝗶𝗻𝘂𝘁𝗲𝘀
Zhanpeng Luo, Haoxi Ran, Li Lu
arxiv.org/abs/2510.01119
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 7d

𝗟𝗩𝗧: 𝗟𝗮𝗿𝗴𝗲-𝗦𝗰𝗮𝗹𝗲 𝗦𝗰𝗲𝗻𝗲 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 𝘃𝗶𝗮 𝗟𝗼𝗰𝗮𝗹 𝗩𝗶𝗲𝘄 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿𝘀
Tooba Imtiaz, Lucy Chai, Kathryn Heal ... John Flynn
arxiv.org/abs/2509.25001
Trending on www.scholar-inbox.com

2

Vision and Graphics Trends @si-cv-graphics.bsky.social · 7d

𝗧𝗿𝗶𝗮𝗻𝗴𝗹𝗲 𝗦𝗽𝗹𝗮𝘁𝘁𝗶𝗻𝗴+: 𝗗𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝘁𝗶𝗮𝗯𝗹𝗲 𝗥𝗲𝗻𝗱𝗲𝗿𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗢𝗽𝗮𝗾𝘂𝗲 𝗧𝗿𝗶𝗮𝗻𝗴𝗹𝗲𝘀
Jan Held, Renaud Vandeghen, Sanghyun Son ... Andrea Tagliasacchi
arxiv.org/abs/2509.25122
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 7d

𝗩𝗚𝗚𝗧-𝗫: 𝗪𝗵𝗲𝗻 𝗩𝗚𝗚𝗧 𝗠𝗲𝗲𝘁𝘀 𝗗𝗲𝗻𝘀𝗲 𝗡𝗼𝘃𝗲𝗹 𝗩𝗶𝗲𝘄 𝗦𝘆𝗻𝘁𝗵𝗲𝘀𝗶𝘀
Yang Liu, Chuanchen Luo, Zimo Tang ... Zhaoxiang Zhang
arxiv.org/abs/2509.25191
Trending on www.scholar-inbox.com

1

Vision and Graphics Trends @si-cv-graphics.bsky.social · 8d

𝗚𝗦-𝟮𝗠: 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗦𝗽𝗹𝗮𝘁𝘁𝗶𝗻𝗴 𝗳𝗼𝗿 𝗝𝗼𝗶𝗻𝘁 𝗠𝗲𝘀𝗵 𝗥𝗲𝗰𝗼𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗠𝗮𝘁𝗲𝗿𝗶𝗮𝗹 𝗗𝗲𝗰𝗼𝗺𝗽𝗼𝘀𝗶𝘁𝗶𝗼𝗻
Dinh Minh Nguyen, Malte Avenhaus, Thomas Lindemeier
arxiv.org/abs/2509.22276
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 8d

𝗟𝗮𝗿𝗴𝗲 𝗠𝗮𝘁𝗲𝗿𝗶𝗮𝗹 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗠𝗼𝗱𝗲𝗹 𝗳𝗼𝗿 𝗥𝗲𝗹𝗶𝗴𝗵𝘁𝗮𝗯𝗹𝗲 𝟯𝗗 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻
Jingrui Ye, Lingting Zhu, Runze Zhang ... Qingmin Liao
arxiv.org/abs/2509.22112
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 8d

𝗙𝗮𝗻𝘁𝗮𝘀𝘆𝗪𝗼𝗿𝗹𝗱: 𝗚𝗲𝗼𝗺𝗲𝘁𝗿𝘆-𝗖𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝘁 𝗪𝗼𝗿𝗹𝗱 𝗠𝗼𝗱𝗲𝗹𝗶𝗻𝗴 𝘃𝗶𝗮 𝗨𝗻𝗶𝗳𝗶𝗲𝗱 𝗩𝗶𝗱𝗲𝗼 𝗮𝗻𝗱 𝟯𝗗 𝗣𝗿𝗲𝗱𝗶𝗰𝘁𝗶𝗼𝗻
Yixiang Dai, Fan Jiang, Chiyu Wang ... Yonggang Qi
arxiv.org/abs/2509.21657
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 9d

𝗗𝗲𝗻𝘀𝗲 𝗦𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝗠𝗮𝘁𝗰𝗵𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗩𝗚𝗚𝗧 𝗣𝗿𝗶𝗼𝗿
Songlin Yang, Tianyi Wei, Yushi Lan ... Xingang Pan
arxiv.org/abs/2509.21263
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 9d

𝗗𝗿𝗮𝗴𝟰𝗗: 𝗔𝗹𝗶𝗴𝗻 𝗬𝗼𝘂𝗿 𝗠𝗼𝘁𝗶𝗼𝗻 𝘄𝗶𝘁𝗵 𝗧𝗲𝘅𝘁-𝗗𝗿𝗶𝘃𝗲𝗻 𝟯𝗗 𝗦𝗰𝗲𝗻𝗲 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻
Minjun Kang, Inkyu Shin, Taeyeop Lee ... Kuk-Jin Yoon
arxiv.org/abs/2509.21888
Trending on www.scholar-inbox.com

Vision and Graphics Trends @si-cv-graphics.bsky.social · 9d

𝗨𝗻𝗶𝗩𝗶𝗱: 𝗨𝗻𝗶𝗳𝘆𝗶𝗻𝗴 𝗩𝗶𝘀𝗶𝗼𝗻 𝗧𝗮𝘀𝗸𝘀 𝘄𝗶𝘁𝗵 𝗣𝗿𝗲-𝘁𝗿𝗮𝗶𝗻𝗲𝗱 𝗩𝗶𝗱𝗲𝗼 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝗠𝗼𝗱𝗲𝗹𝘀
Lan Chen, Yuchao Gu, Qi Mao
arxiv.org/abs/2509.21760
Trending on www.scholar-inbox.com

1

Vision and Graphics Trends @si-cv-graphics.bsky.social · 10d

𝗠𝗼𝘁𝗶𝗼𝗻𝗙𝗹𝗼𝘄:𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗜𝗺𝗽𝗹𝗶𝗰𝗶𝘁 𝗠𝗼𝘁𝗶𝗼𝗻 𝗙𝗹𝗼𝘄 𝗳𝗼𝗿 𝗖𝗼𝗺𝗽𝗹𝗲𝘅 𝗖𝗮𝗺𝗲𝗿𝗮 𝗧𝗿𝗮𝗷𝗲𝗰𝘁𝗼𝗿𝘆 𝗖𝗼𝗻𝘁𝗿𝗼𝗹 𝗶𝗻 𝗩𝗶𝗱𝗲𝗼 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻
Guojun Lei, Chi Wang, Yikai Wang ... Weiwei Xu
arxiv.org/abs/2509.21119
Trending on www.scholar-inbox.com

1