{"ID":2864900,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21719","arxiv_id":"2509.21719","title":"DeLiVR: Differential Spatiotemporal Lie Bias for Efficient Video Deraining","abstract":"Videos captured in the wild often suffer from rain streaks, blur, and noise. In addition, even slight changes in camera pose can amplify cross-frame mismatches and temporal artifacts. Existing methods rely on optical flow or heuristic alignment, which are computationally expensive and less robust. To address these challenges, Lie groups provide a principled way to represent continuous geometric transformations, making them well-suited for enforcing spatial and temporal consistency in video modeling. Building on this insight, we propose DeLiVR, an efficient video deraining method that injects spatiotemporal Lie-group differential biases directly into attention scores of the network. Specifically, the method introduces two complementary components. First, a rotation-bounded Lie relative bias predicts the in-plane angle of each frame using a compact prediction module, where normalized coordinates are rotated and compared with base coordinates to achieve geometry-consistent alignment before feature aggregation. Second, a differential group displacement computes angular differences between adjacent frames to estimate a velocity. This bias computation combines temporal decay and attention masks to focus on inter-frame relationships while precisely matching the direction of rain streaks. Extensive experimental results demonstrate the effectiveness of our method on publicly available benchmarks. The code is publicly available at https://github.com/Shuning0312/ICLR-DeLiVR.","short_abstract":"Videos captured in the wild often suffer from rain streaks, blur, and noise. In addition, even slight changes in camera pose can amplify cross-frame mismatches and temporal artifacts. Existing methods rely on optical flow or heuristic alignment, which are computationally expensive and less robust. To address these chal...","url_abs":"https://arxiv.org/abs/2509.21719","url_pdf":"https://arxiv.org/pdf/2509.21719v2","authors":"[\"Shuning Sun\",\"Jialang Lu\",\"Xiang Chen\",\"Jichao Wang\",\"Dianjie Lu\",\"Guijuan Zhang\",\"Guangwei Gao\",\"Zhuoran Zheng\"]","published":"2025-09-26T00:29:36Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":609211,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2864900,"paper_url":"https://arxiv.org/abs/2509.21719","paper_title":"DeLiVR: Differential Spatiotemporal Lie Bias for Efficient Video Deraining","repo_url":"https://github.com/Shuning0312/ICLR-DeLiVR","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}