{"ID":2838504,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.17059","arxiv_id":"2511.17059","title":"REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting","abstract":"Articulated objects are pervasive in daily environments, such as drawers and refrigerators. Towards their part-level surface reconstruction and joint parameter estimation, REArtGS introduces a category-agnostic approach using multi-view RGB images at two different states. However, we observe that REArtGS still struggles with screw-joint or multi-part objects and lacks geometric constraints for unseen states. In this paper, we propose REArtGS++, a novel method towards generalizable articulated object reconstruction with temporal geometry constraint and planar Gaussian splatting. We first model a decoupled screw motion for each joint without type prior, and jointly optimize part-aware Gaussians with joint parameters through part motion blending. To introduce time-continuous geometric constraint for articulated modeling, we encourage Gaussians to be planar and propose a temporally consistent regularization between planar normal and depth through Taylor first-order expansion. Extensive experiments on both synthetic and real-world articulated objects demonstrate our superiority in generalizable part-level surface reconstruction and joint parameter estimation, compared to existing approaches. Project Site: https://sites.google.com/view/reartgs2/home.","short_abstract":"Articulated objects are pervasive in daily environments, such as drawers and refrigerators. Towards their part-level surface reconstruction and joint parameter estimation, REArtGS introduces a category-agnostic approach using multi-view RGB images at two different states. However, we observe that REArtGS still struggle...","url_abs":"https://arxiv.org/abs/2511.17059","url_pdf":"https://arxiv.org/pdf/2511.17059v3","authors":"[\"Di Wu\",\"Liu Liu\",\"Anran Huang\",\"Yuyan Liu\",\"Qiaojun Yu\",\"Shaofan Liu\",\"Liangtu Song\",\"Cewu Lu\"]","published":"2025-11-21T09:07:56Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","project_urls":"[\"https://sites.google.com/view/reartgs2/home\"]","has_code":false,"code_links":[{"ID":606781,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2838504,"paper_url":"https://arxiv.org/abs/2511.17059","paper_title":"REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting","repo_url":"https://github.com/google/safevalues","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}