{"ID":2888493,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.23782","arxiv_id":"2507.23782","title":"MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion","abstract":"We address the problem of dynamic scene reconstruction from sparse-view videos. Prior work often requires dense multi-view captures with hundreds of calibrated cameras (e.g. Panoptic Studio). Such multi-view setups are prohibitively expensive to build and cannot capture diverse scenes in-the-wild. In contrast, we aim to reconstruct dynamic human behaviors, such as repairing a bike or dancing, from a small set of sparse-view cameras with complete scene coverage (e.g. four equidistant inward-facing static cameras). We find that dense multi-view reconstruction methods struggle to adapt to this sparse-view setup due to limited overlap between viewpoints. To address these limitations, we carefully align independent monocular reconstructions of each camera to produce time- and view-consistent dynamic scene reconstructions. Extensive experiments on PanopticStudio and Ego-Exo4D demonstrate that our method achieves higher quality reconstructions than prior art, particularly when rendering novel views. Code, data, and data-processing scripts are available on https://github.com/Z1hanW/MonoFusion.","short_abstract":"We address the problem of dynamic scene reconstruction from sparse-view videos. Prior work often requires dense multi-view captures with hundreds of calibrated cameras (e.g. Panoptic Studio). Such multi-view setups are prohibitively expensive to build and cannot capture diverse scenes in-the-wild. In contrast, we aim t...","url_abs":"https://arxiv.org/abs/2507.23782","url_pdf":"https://arxiv.org/pdf/2507.23782v2","authors":"[\"Zihan Wang\",\"Jeff Tan\",\"Tarasha Khurana\",\"Neehar Peri\",\"Deva Ramanan\"]","published":"2025-07-31T17:59:32Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":611549,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2888493,"paper_url":"https://arxiv.org/abs/2507.23782","paper_title":"MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion","repo_url":"https://github.com/Z1hanW/MonoFusion","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}