[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-2282":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":9,"rankLanguage":9,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":9,"pushedAt":9,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":15,"starSnapshotCount":15,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},2282,"top-cvpr-2026-papers","SkalskiP\u002Ftop-cvpr-2026-papers","SkalskiP","About This repository is a curated collection of the most exciting and influential CVPR 2026 papers. 🔥 [Paper + Code + Demo]",null,"Python",434,24,6,1,0,78,141,326,234,4.19,"Creative Commons Zero v1.0 Universal",false,"master",true,[],"2026-06-12 02:00:39","![visitor badge](https:\u002F\u002Fvisitor-badge.laobi.icu\u002Fbadge?page_id=SkalskiP.top-cvpr-2026-papers)\n\n\u003Cdiv align=\"center\">\n  \u003Ch1 align=\"center\">top CVPR 2026 papers\u003C\u002Fh1>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSkalskiP\u002Ftop-cvpr-2023-papers\">2023\u003C\u002Fa> | \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSkalskiP\u002Ftop-cvpr-2024-papers\">2024\u003C\u002Fa> | \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSkalskiP\u002Ftop-cvpr-2025-papers\">2025\u003C\u002Fa> | \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSkalskiP\u002Ftop-cvpr-2026-papers\">2026\u003C\u002Fa>\n\u003C\u002Fdiv>\n\n## 👋 hello\n\nComputer Vision and Pattern Recognition is a massive conference. In **2026** alone,\n**16,092** papers were submitted, and **4,090** were accepted. I created this repository\nto help you search for crème de la crème of CVPR publications. If the paper you are\nlooking for is not on my short list, take a peek at the full\n[list](https:\u002F\u002Fcvpr.thecvf.com\u002FConferences\u002F2026\u002FAcceptedPapers) of accepted papers.\n\n## 🗞️ papers and posters\n\n*📢 - oral | 🔥 - highlight | 🏆 - best paper*\n\n\u003C!--- AUTOGENERATED_PAPERS_LIST -->\n\u003C!---\n   WARNING: DO NOT EDIT THIS LIST MANUALLY. IT IS AUTOMATICALLY GENERATED.\n   HEAD OVER TO https:\u002F\u002Fgithub.com\u002FSkalskiP\u002Ftop-cvpr-2026-papers\u002Fblob\u002Fmaster\u002FCONTRIBUTING.md FOR MORE DETAILS ON HOW TO MAKE CHANGES PROPERLY.\n-->\n### 3d vision\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F39508.png?t=1779316577.0970874\" title=\"SAM 3D: 3Dfy Anything in Images\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F39508.png\" alt=\"SAM 3D: 3Dfy Anything in Images\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.16624\" title=\"SAM 3D: 3Dfy Anything in Images\">\n        \u003Cstrong>🏆 SAM 3D: 3Dfy Anything in Images\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Jianing Yang, Georgia Gkioxari, Anushka Sagar, Aohan Lin, Bowen Song, Bowen Zhang, Fu-Jen Chu, Hao Tang, ...\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.16624\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fsam-3d-objects\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=7Zda9tHhVIg\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> 3D Vision\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Fri 5 Jun 13:00-14:15 Oral Session 2A #5 | Fri 5 Jun 16:00-18:00 Poster Session 2 #5\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F38552.png?t=1779278305.871803\" title=\"B³-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta-Bernoulli Bayesian Updates\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F38552.png\" alt=\"B³-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta-Bernoulli Bayesian Updates\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.17134\" title=\"B³-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta-Bernoulli Bayesian Updates\">\n        \u003Cstrong>🔥 B³-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta-Bernoulli Bayesian Updates\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Hiromichi Kamata, Samuel Arthur Munro, Fuminori Homma\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.17134\">paper\u003C\u002Fa>]  [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=w-bjx9la2WY\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> 3D Vision\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sat 6 Jun 16:45-18:45 Poster Session 4 #507\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F38780.png?t=1779273919.6110525\" title=\"Efficiently Reconstructing Dynamic Scenes One D4RT at a Time\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F38780.png\" alt=\"Efficiently Reconstructing Dynamic Scenes One D4RT at a Time\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.08924\" title=\"Efficiently Reconstructing Dynamic Scenes One D4RT at a Time\">\n        \u003Cstrong>🔥 Efficiently Reconstructing Dynamic Scenes One D4RT at a Time\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Chuhan Zhang, Guillaume Le Moing, Skanda Koppula, Ignacio Rocco, Liliane Momeni, Junyu Xie, Shuyang Sun, Rahul Sukthankar, ...\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.08924\">paper\u003C\u002Fa>]  [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4u5JxhyZ86g\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> 3D Vision\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Fri 5 Jun 13:00-14:15 Oral Session 2D #2 | Fri 5 Jun 16:00-18:00 Poster Session 2 #20\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.17012\" title=\"4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation\">\n        \u003Cstrong>🔥 4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Chiao-An Yang, Ryo Hachiuma, Sifei Liu, Subhashree Radhakrishnan, Raymond A. Yeh, Yu-Chiang Frank Wang, Min-Hung Chen\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.17012\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FNVlabs\u002F4D-RGPT\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Q4WCHmUDbBM\">video\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fnvidia\u002FR4D-Bench\">demo\u003C\u002Fa>] \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> 3D Vision\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sun 7 Jun 11:45-13:45 Poster Session 5 #225\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F39357.png?t=1779383580.1341395\" title=\"Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F39357.png\" alt=\"Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.26488\" title=\"Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners\">\n        \u003Cstrong>📢 Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Nikita Araslanov, Martin Sundermeyer, Hidenobu Matsuki, David Joseph Tan, Federico Tombari\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.26488\">paper\u003C\u002Fa>]  [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=gLIRCCtzOyI\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> 3D Vision\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sat 6 Jun 14:00-15:15 Oral Session 4A: Geometric Understanding #2 | Sat 6 Jun 16:45-18:45 Poster Session 4 #2\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F37717.png?t=1779382307.4573128\" title=\"MuM: Multi-View Masked Image Modeling for 3D Vision\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F37717.png\" alt=\"MuM: Multi-View Masked Image Modeling for 3D Vision\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.17309\" title=\"MuM: Multi-View Masked Image Modeling for 3D Vision\">\n        \u003Cstrong>MuM: Multi-View Masked Image Modeling for 3D Vision\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    David Nordström, Johan Edstedt, Fredrik Kahl, Georg Bökman\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.17309\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fdavnords\u002FMuM\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=poPwO2Wz-rY\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> 3D Vision\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sat 6 Jun 16:45-18:45 Poster Session 4 #28\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F38436.png?t=1779529020.490129\" title=\"Emergent Outlier View Rejection in Visual Geometry Grounded Transformers\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F38436.png\" alt=\"Emergent Outlier View Rejection in Visual Geometry Grounded Transformers\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.04012\" title=\"Emergent Outlier View Rejection in Visual Geometry Grounded Transformers\">\n        \u003Cstrong>Emergent Outlier View Rejection in Visual Geometry Grounded Transformers\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Jisang Han, Sunghwan Hong, Jaewoo Jung, Wooseok Jang, Honggyu An, Qianqian Wang, Seungryong Kim, Chen Feng\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.04012\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fcvlab-kaist\u002FRobustVGGT\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=-eaSEyiGgP8\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> 3D Vision\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Fri 5 Jun 10:45-12:45 Poster Session 1 #41\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F36715.png?t=1779240845.570811\" title=\"AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localization\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F36715.png\" alt=\"AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localization\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.09445\" title=\"AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localization\">\n        \u003Cstrong>🔥 AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localization\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Mohammad Omama, Gabriele Berton, Eric Foxlin, Yelin Kim\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.09445\">paper\u003C\u002Fa>]    \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> 3D Vision\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sat 6 Jun 16:45-18:45 Poster Session 4 #467\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F38483.png?t=1778703289.4757984\" title=\"tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F38483.png\" alt=\"tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.20160\" title=\"tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction\">\n        \u003Cstrong>🔥 tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Chen Wang, Hao Tan, Wang Yifan, Zhiqin Chen, Yuheng Liu, Kalyan Sunkavalli, Sai Bi, Lingjie Liu, ...\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.20160\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fcwchenwang\u002FtttLRM\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=uOlNkq_io4c\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> 3D Vision\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sun 7 Jun 15:30-17:30 Poster Session 6 #39\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n### depth estimation\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.16913\" title=\"Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation\">\n        \u003Cstrong>Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Xin Lin, Meixi Song, Dizhe Zhang, Wenxuan Lu, Haodong Li, Bo Du, Ming-Hsuan Yang, Truong Nguyen, ...\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.16913\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FInsta360-Research-Team\u002FDAP\">code\u003C\u002Fa>]  [\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fspaces\u002FInsta360-Research\u002FDAP\">demo\u003C\u002Fa>] \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Depth Estimation\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sat 6 Jun 16:45-18:45 Poster Session 4 #504\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\n### generative models\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.08269\" title=\"EgoX: Egocentric Video Generation from a Single Exocentric Video\">\n        \u003Cstrong>EgoX: Egocentric Video Generation from a Single Exocentric Video\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Taewoong Kang, Kinam Kim, Keunwoo Park, Seonghyeon Park, Youngjoon Yu, Seunghoon Hong\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.08269\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FDAVIAN-Robotics\u002FEgoX\">code\u003C\u002Fa>]   \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Generative Models\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Fri 5 Jun 16:00-18:00 Poster Session 2 #366\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.13720\" title=\"Back to Basics: Let Denoising Generative Models Denoise\">\n        \u003Cstrong>Back to Basics: Let Denoising Generative Models Denoise\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Tianhong Li, Kaiming He\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.13720\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FLTH14\u002FJiT\">code\u003C\u002Fa>]   \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Generative Models\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sun 7 Jun 11:45-13:45 Poster Session 5 #700\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F36668.png?t=1779199620.586524\" title=\"MacTok: Robust Continuous Tokenization for Image Generation\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F36668.png\" alt=\"MacTok: Robust Continuous Tokenization for Image Generation\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.29634\" title=\"MacTok: Robust Continuous Tokenization for Image Generation\">\n        \u003Cstrong>🔥 MacTok: Robust Continuous Tokenization for Image Generation\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Hengyu Zeng, Xin Gao, Guanghao Li, Yuxiang Yan, Jiaoyang Ruan, Junpeng Ma, Haoyu Albert Wang, Jian Pu\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.29634\">paper\u003C\u002Fa>]  [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=w5uNGlWy778\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Generative Models\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sun 7 Jun 15:30-17:30 Poster Session 6 #672\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F38021.png?t=1779748078.4763258\" title=\"A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F38021.png\" alt=\"A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.04913\" title=\"A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens\">\n        \u003Cstrong>🔥 A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Tommie Kerssies, Gabriele Berton, Ju He, Qihang Yu, Wufei Ma, Daan de Geus, Gijs Dubbelman, Liang-Chieh Chen\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.04913\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Famazon-far\u002Fdeltatok\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=D6yW9J8_HvE\">video\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fcollections\u002FAmazon-FAR\u002Fdeltatok\">demo\u003C\u002Fa>] \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Generative Models\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sat 6 Jun 16:45-18:45 Poster Session 4 #611\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n### object detection\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F39842.png?t=1778984010.97555\" title=\"Does YOLO Really Need to See Every Training Image in Every Epoch?\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F39842.png\" alt=\"Does YOLO Really Need to See Every Training Image in Every Epoch?\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.17684\" title=\"Does YOLO Really Need to See Every Training Image in Every Epoch?\">\n        \u003Cstrong>📢 Does YOLO Really Need to See Every Training Image in Every Epoch?\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Xingxing Xie, Jiahua Dong, Junwei Han, Gong Cheng\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.17684\">paper\u003C\u002Fa>]  [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=TfEgVtbZIx0\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Object Detection\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Fri 5 Jun 9:15-10:30 Oral Session 1C #2 | Fri 5 Jun 10:45-12:45 Poster Session 1 #14\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n### object tracking\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F38132.png?t=1779014745.6748493\" title=\"V²-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F38132.png\" alt=\"V²-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.20886\" title=\"V²-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence\">\n        \u003Cstrong>🔥 V²-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Jiancheng Pan, Runze Wang, Tianwen Qian, Mohammad Mahdi, Yanwei Fu, Xiangyang Xue, Xiaomeng Huang, Luc Van Gool, ...\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.20886\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fjaychempan\u002FV2-SAM\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ieQ2AW3k0W4\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Object Tracking\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sat 6 Jun 11:45-13:45 Poster Session 3 #248\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F36388.png?t=1778878578.5070403\" title=\"Real-World Point Tracking with Verifier-Guided Pseudo-Labeling\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F36388.png\" alt=\"Real-World Point Tracking with Verifier-Guided Pseudo-Labeling\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.12217\" title=\"Real-World Point Tracking with Verifier-Guided Pseudo-Labeling\">\n        \u003Cstrong>🔥 Real-World Point Tracking with Verifier-Guided Pseudo-Labeling\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Görkay Aydemir, Fatma Güney, Weidi Xie\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.12217\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fgorkaydemir\u002Ftrack_on\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Ip9hSov6qVQ\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Object Tracking\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Fri 5 Jun 16:00-18:00 Poster Session 2 #593\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n### physical modeling\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F38086.png?t=1778680352.3420095\" title=\"MSPT: Efficient Large-Scale Physical Modeling via Parallelized Multi-Scale Attention\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F38086.png\" alt=\"MSPT: Efficient Large-Scale Physical Modeling via Parallelized Multi-Scale Attention\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.01738\" title=\"MSPT: Efficient Large-Scale Physical Modeling via Parallelized Multi-Scale Attention\">\n        \u003Cstrong>🔥 MSPT: Efficient Large-Scale Physical Modeling via Parallelized Multi-Scale Attention\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Pedro M. P. Curvo, Jan-Willem van de Meent, Maksim Zhdanov\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.01738\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fpedrocurvo\u002Fmspt\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=oOHYwosKg6g\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Physical Modeling\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Fri 5 Jun 16:00-18:00 Poster Session 2 #534\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n### pose estimation\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F37714.png?t=1779474509.2077193\" title=\"SAM 3D Body: Robust Full-Body Human Mesh Recovery\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F37714.png\" alt=\"SAM 3D Body: Robust Full-Body Human Mesh Recovery\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.15989\" title=\"SAM 3D Body: Robust Full-Body Human Mesh Recovery\">\n        \u003Cstrong>🏆 SAM 3D Body: Robust Full-Body Human Mesh Recovery\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Xitong Yang, Devansh Kukreja, Don Pinkus, Anushka Sagar, Taosha Fan, Jinhyung Park, Soyong Shin, Jinkun Cao, ...\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.15989\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fsam-3d-body\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=B7PZuM55ayc\">video\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fakhaliq\u002Fsam-3d-body\">demo\u003C\u002Fa>] \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Pose Estimation\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Fri 5 Jun 13:00-14:15 Oral Session 2A #4 | Fri 5 Jun 16:00-18:00 Poster Session 2 #4\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F38362.png?t=1779290919.2415\" title=\"FMPose3D: monocular 3D pose estimation via flow matching\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F38362.png\" alt=\"FMPose3D: monocular 3D pose estimation via flow matching\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.05755\" title=\"FMPose3D: monocular 3D pose estimation via flow matching\">\n        \u003Cstrong>FMPose3D: monocular 3D pose estimation via flow matching\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Ti Wang, Xiaohang Yu, Mackenzie Weygandt Mathis\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.05755\">paper\u003C\u002Fa>]  [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=_aUL-QLqeJM\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Pose Estimation\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sat 6 Jun 11:45-13:45 Poster Session 3 #40\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n### segmentation\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.17807\" title=\"VidEoMT: Your ViT is Secretly Also a Video Segmentation Model\">\n        \u003Cstrong>VidEoMT: Your ViT is Secretly Also a Video Segmentation Model\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Narges Norouzi, Idil Esen Zulfikar, Niccolò Cavagnero, Tommie Kerssies, Bastian Leibe, Gijs Dubbelman, Daan de Geus\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.17807\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftue-mps\u002Fvideomt\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=TlPiGQJSEjI\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Segmentation\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sun 7 Jun 10:15-11:30 Poster Session 5 #611\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.11782\" title=\"MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator\">\n        \u003Cstrong>MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Peiqing Yang, Shangchen Zhou, Kai Hao, Qingyi Tao\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2512.11782\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fpq-yang\u002FMatAnyone2\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=tyi8CNyjOhc\">video\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fspaces\u002FPeiqingYang\u002FMatAnyone\">demo\u003C\u002Fa>] \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Segmentation\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sun 7 Jun 15:30-17:30 Poster Session 6\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.28480\" title=\"INSID3: Training-Free In-Context Segmentation with DINOv3\">\n        \u003Cstrong>📢 INSID3: Training-Free In-Context Segmentation with DINOv3\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Claudia Cuttano, Gabriele Trivigno, Christoph Reich, Daniel Cremers, Carlo Masone, Stefan Roth\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.28480\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvisinf\u002FINSID3\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=J5KqA3rnUTE\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Segmentation\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sat 6 Jun 14:00-15:15 Oral Session 4D: Visual Segmentation #1 | Sat 6 Jun 16:45-18:45 Poster Session 4 #19\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.15622\" title=\"The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identification\">\n        \u003Cstrong>📢 The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identification\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Dante Francisco Wasmuht, Otto Brookes, Maximillian Schall, Pablo Palencia, Chris Beirne, Tilo Burghardt, Majid Mirmehdi, Hjalmar Kühl, ...\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.15622\">paper\u003C\u002Fa>]   [\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Ffacebook\u002FSA-FARI\">demo\u003C\u002Fa>] \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Segmentation\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sat 6 Jun 14:00-15:15 Oral Session 4D: Visual Segmentation #5 | Sat 6 Jun 16:45-18:45 Poster Session 4 #23\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.18267\" title=\"MARCO: Navigating the Unseen Space of Semantic Correspondence\">\n        \u003Cstrong>📢 MARCO: Navigating the Unseen Space of Semantic Correspondence\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Claudia Cuttano, Gabriele Trivigno, Carlo Masone, Stefan Roth\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.18267\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvisinf\u002FMARCO\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=paYaAh-fkYg\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Segmentation\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sat 6 Jun 14:00-15:15 Oral Session 4D: Visual Segmentation #2 | Sat 6 Jun 16:45-18:45 Poster Session 4 #20\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F37369.png?t=1779154215.1613407\" title=\"VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F37369.png\" alt=\"VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.13596\" title=\"VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation\">\n        \u003Cstrong>📢 VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Yulu Gao, Bohao Zhang, Zongheng Tang, Jitong Liao, Wenjun Wu, Si Liu\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.13596\">paper\u003C\u002Fa>]  [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=56TSdPqQtgA\">video\u003C\u002Fa>]  \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Segmentation\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sat 6 Jun 14:00-15:15 Oral Session 4D: Visual Segmentation #6 | Sat 6 Jun 16:45-18:45 Poster Session 4 #24\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n### vision-language models\n\n\u003Cp align=\"left\">\n    \u003Ca href=\"https:\u002F\u002Fcvpr.thecvf.com\u002Fmedia\u002FPosterPDFs\u002FCVPR%202026\u002F36664.png?t=1779392281.6248565\" title=\"TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment\">\n        \u003Cimg src=\"https:\u002F\u002Fstorage.googleapis.com\u002Fcom-roboflow-marketing\u002Fcvpr-2026-posters\u002F36664.png\" alt=\"TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment\" width=\"400px\" align=\"left\" \u002F>\n    \u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.12012\" title=\"TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment\">\n        \u003Cstrong>TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment\u003C\u002Fstrong>\n    \u003C\u002Fa>\n    \u003Cbr\u002F>\n    Bingyi Cao, Koert Chen, Kevis-Kokitsi Maninis, Kaifeng Chen, Arjun Karpur, Ye Xia, Sahil Dua, Tanmaya Dabral, ...\n    \u003Cbr\u002F>\n    [\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.12012\">paper\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fgoogle-deepmind\u002Ftips\">code\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=vERsVd58ta0\">video\u003C\u002Fa>] [\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fgoogle\u002FTIPSv2\">demo\u003C\u002Fa>] \n    \u003Cbr\u002F>\n    \u003Cstrong>Topic:\u003C\u002Fstrong> Vision-Language Models\n    \u003Cbr\u002F>\n    \u003Cstrong>Session:\u003C\u002Fstrong> Sun 7 Jun 11:45-13:45 Poster Session 5 #65\n\u003C\u002Fp>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n\u003C!--- AUTOGENERATED_PAPERS_LIST -->\n\n## 🦸 contribution\n\nWe would love your help in making this repository even better! If you know of an amazing\npaper that isn't listed here, or if you have any suggestions for improvement, feel free\nto open an\n[issue](https:\u002F\u002Fgithub.com\u002FSkalskiP\u002Ftop-cvpr-2026-papers\u002Fissues)\nor submit a\n[pull request](https:\u002F\u002Fgithub.com\u002FSkalskiP\u002Ftop-cvpr-2026-papers\u002Fpulls).\n","该项目是一个精心整理的CVPR 2026顶级论文集合，包含了该年度最具影响力和创新性的计算机视觉研究成果。核心功能包括提供每篇论文的链接、代码仓库以及演示视频或海报，便于研究者快速访问和复现相关工作。技术特点上，项目利用自动化脚本生成并维护论文列表，确保信息的准确性和时效性。适合从事计算机视觉领域研究的学生、学者及工程师使用，尤其对于希望紧跟最新科研动态或寻找特定方向突破灵感的人来说非常有价值。",2,"2026-06-11 02:49:14","CREATED_QUERY"]