{"ID":6497812,"CreatedAt":"2026-07-13T01:19:40.13847098Z","UpdatedAt":"2026-07-14T15:06:33.663243204Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.09125","arxiv_id":"2607.09125","title":"4D Human-Scene Reconstruction from Low-Overlap Captures","abstract":"Existing volumetric capture of dynamic human performance achieves high fidelity with dense camera arrays. However, in real-world scenarios, only a handful of low-overlap cameras are available, which degrades the output quality and leaves large areas unobserved. Recent 4D reconstruction methods have focused on low-overlap settings, yet they still produce noticeable artifacts in under-observed regions. Video diffusion models have emerged as another option, but they show geometrically inconsistent results for humans. To address these limitations, we propose StudioRecon, a pipeline that reconstructs 4D human scenes from sparse, low-overlap cameras by decoupling background and humans. We densify background supervision by synthesizing hundreds of camera-controlled novel views with a video diffusion model. We also robustly initialize deformable Gaussian humans with cross-view identity association and triangulated multi-view keypoint fitting. Finally, our recursive enhancement module with motion-adaptive consistency injection harmonizes the composed output, thereby further avoiding remaining artifacts. We achieve state-of-the-art novel view synthesis across four real-world datasets and demonstrate applications such as novel trajectory rendering and human replacement.","short_abstract":"Existing volumetric capture of dynamic human performance achieves high fidelity with dense camera arrays. However, in real-world scenarios, only a handful of low-overlap cameras are available, which degrades the output quality and leaves large areas unobserved. Recent 4D reconstruction methods have focused on low-overl...","url_abs":"https://arxiv.org/abs/2607.09125","url_pdf":"https://arxiv.org/pdf/2607.09125v1","authors":"[\"Minhyuk Hwang\",\"Sangmin Kim\",\"Seunguk Do\",\"Daneul Kim\",\"Jaesik Park\"]","published":"2026-07-10T06:30:45Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}