{"ID":2874337,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.05296","arxiv_id":"2509.05296","title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool","abstract":"We present WinT3R, a feed-forward reconstruction model capable of online prediction of precise camera poses and high-quality point maps. Previous methods suffer from a trade-off between reconstruction quality and real-time performance. To address this, we first introduce a sliding window mechanism that ensures sufficient information exchange among frames within the window, thereby improving the quality of geometric predictions without large computation. In addition, we leverage a compact representation of cameras and maintain a global camera token pool, which enhances the reliability of camera pose estimation without sacrificing efficiency. These designs enable WinT3R to achieve state-of-the-art performance in terms of online reconstruction quality, camera pose estimation, and reconstruction speed, as validated by extensive experiments on diverse datasets. Code and model are publicly available at https://github.com/LiZizun/WinT3R.","short_abstract":"We present WinT3R, a feed-forward reconstruction model capable of online prediction of precise camera poses and high-quality point maps. Previous methods suffer from a trade-off between reconstruction quality and real-time performance. To address this, we first introduce a sliding window mechanism that ensures sufficie...","url_abs":"https://arxiv.org/abs/2509.05296","url_pdf":"https://arxiv.org/pdf/2509.05296v1","authors":"[\"Zizun Li\",\"Jianjun Zhou\",\"Yifan Wang\",\"Haoyu Guo\",\"Wenzheng Chang\",\"Yang Zhou\",\"Haoyi Zhu\",\"Junyi Chen\",\"Chunhua Shen\",\"Tong He\"]","published":"2025-09-05T17:59:47Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":610131,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2874337,"paper_url":"https://arxiv.org/abs/2509.05296","paper_title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool","repo_url":"https://github.com/LiZizun/WinT3R","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}