{"ID":5438618,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T04:20:05.427450767Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31115","arxiv_id":"2606.31115","title":"JacobianAvatar: Temporally Consistent Semi-rigid Avatar Reconstruction from a Monocular Video","abstract":"Generating realistic human avatars in complex motions--such as clothing dynamics--requires modeling of global and local deformations which remains challenging in monocular settings. We address this problem by leveraging neural Jacobian fields (NJFs) for representing semi-rigid deformations. We train self-supervised neural networks for predicting Jacobian matrices that give the pose-dependent deformations, by solving a Poisson equation. However, monocular input presents several difficulties such as self-occluded regions and invisible surfaces. To address these issues, we introduce three key components: a constrained Poisson solver, signed distance-based Jacobian regularization, and a deformation-guided residual flow loss, which together suppress boundary artifacts, recover frequently occluded regions such as armpits and thighs, and enforce temporal consistency during motion. Experiments on benchmark and in-the-wild videos demonstrate that our method generates temporally stable and geometrically coherent avatars, outperforming state-of-the-art approaches.","short_abstract":"Generating realistic human avatars in complex motions--such as clothing dynamics--requires modeling of global and local deformations which remains challenging in monocular settings. We address this problem by leveraging neural Jacobian fields (NJFs) for representing semi-rigid deformations. We train self-supervised neu...","url_abs":"https://arxiv.org/abs/2606.31115","url_pdf":"https://arxiv.org/pdf/2606.31115v1","authors":"[\"Changyeon Won\",\"Min-Gyu Park\",\"Seonghwan Park\",\"Ju Hong Yoon\",\"Hae-Gon Jeon\"]","published":"2026-06-30T04:22:16Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}