4D Human-Scene Reconstruction from Low-Overlap Captures

• URL: http://arxiv.org/abs/2607.09125v1
• Date: Fri, 10 Jul 2026 06:30:45 GMT
• Title: 4D Human-Scene Reconstruction from Low-Overlap Captures
• Abstract summary: In real-world scenarios, only a handful of low-overlap cameras are available, which degrades the output quality.<n>Recent 4D reconstruction methods have focused on low-overlap settings, yet they still produce noticeable artifacts in under-observed regions.<n>We propose StudioRecon, a pipeline that reconstructs 4D human scenes from sparse, low-overlap cameras by decoupling background and humans.
• Score: 32.94451563162227
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• GUSH3R: Everyone Everywhere All at Once as Gaussians [30.884035795245946]
  We present GUSH3R (Gaussian-Unified Scene Human 3D Reconstruction), a feed-forward framework for online dynamic human-scene reconstruction.<n>From a monocular human-scene video, our method reconstructs dynamic humans (everyone) and static scenes (everywhere) in a single forward pass.<n>Experiments on monocular human-scene datasets demonstrate that our approach achieves competitive novel view synthesis quality.
  arXiv  Detail & Related papers  (2026-07-06T15:53:09Z)
• 4D Reconstruction from Sparse Dynamic Cameras [32.72043828725801]
  We focus on an alternative practical way, i.e. sparse dynamic camera setup, where a handful of cameras capture the same subjects.<n>This setup introduces multi-view constraints and remains practical for real-world video production such as sports, concerts, and TV shows.<n>We introduce LetCamsGo, a new real-world video dataset with 5 sequences across 4 diverse environments recorded by three independently moving cameras and one fixed camera.
  arXiv  Detail & Related papers  (2026-06-03T08:31:43Z)
• Syn4D: A Multiview Synthetic 4D Dataset [92.50132053229817]
  3D reconstruction and tracking of dynamic scenes from monocular video remains an important open challenge in computer vision.<n>To address this limitation, we introduce Syn4D, a multiview synthetic dynamic scenes.<n>Key feature of Syn4D is the ability to unproject any pixel into 3D.
  arXiv  Detail & Related papers  (2026-05-06T17:59:55Z)
• Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting [3.1328424544428852]
  We create a framework capable of leveraging internet-scale monocular videos.<n>Our core contribution is the generation of pseudo multi-view training triplets, consisting of a source video, a geometric anchor, and a target video.<n>At inference, our diffusion transformer utilizes a 4D point-cloud derived anchor to achieve state-of-the-art temporal consistency.
  arXiv  Detail & Related papers  (2026-04-23T15:32:56Z)
• 4C4D: 4 Camera 4D Gaussian Splatting [56.926598190499156]
  This paper tackles the challenge of recovering 4D dynamic scenes from videos captured by as few as four portable cameras.<n>We propose textbf4C4D, a novel framework that enables high-fidelity 4D Gaussian Splatting from video captures of extremely sparse cameras.
  arXiv  Detail & Related papers  (2026-04-05T11:09:23Z)
• SparseCam4D: Spatio-Temporally Consistent 4D Reconstruction from Sparse Cameras [13.258108161849727]
  High-quality dynamic scenes typically require dense arrays or even hundreds of synchronized cameras.<n>We propose a sparse-camera dynamic reconstruction framework that exploits abundant yet inconsistent generative observations.<n>We develop a complete pipeline that enables 4D reconstruction from sparse and uncalibrated camera inputs.
  arXiv  Detail & Related papers  (2026-03-27T14:44:52Z)
• LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models [52.656349227001925]
  Given a monocular video, the goal of video re-rendering is to generate views of the scene from a novel camera trajectory.<n>Existing methods face two distinct challenges.<n>We propose to address these challenges by using the implicit geometric knowledge embedded in the latent space of a large 4D reconstruction model.
  arXiv  Detail & Related papers  (2026-01-21T05:46:03Z)
• Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models [83.76517697509156]
  This paper addresses the challenge of high-fidelity view synthesis of humans with sparse-view videos as input.<n>We propose a novel iterative sliding denoising process to enhance view-temporal consistency of the 4D diffusion model.<n>Our method is able to synthesize high-quality and consistent novel-view videos and significantly outperforms the existing approaches.
  arXiv  Detail & Related papers  (2025-07-17T17:59:17Z)
• UAV4D: Dynamic Neural Rendering of Human-Centric UAV Imagery using Gaussian Splatting [54.883935964137706]
  We introduce UAV4D, a framework for enabling photorealistic rendering for dynamic real-world scenes captured by UAVs.<n>We use a combination of a 3D foundation model and a human mesh reconstruction model to reconstruct both the scene background and humans.<n>Our results demonstrate the benefits of our approach over existing methods in novel view synthesis, achieving a 1.5 dB PSNR improvement and superior visual sharpness.
  arXiv  Detail & Related papers  (2025-06-05T13:21:09Z)
• Learning Dynamic View Synthesis With Few RGBD Cameras [60.36357774688289]
  We propose to utilize RGBD cameras to synthesize free-viewpoint videos of dynamic indoor scenes. We generate point clouds from RGBD frames and then render them into free-viewpoint videos via a neural feature. We introduce a simple Regional Depth-Inpainting module that adaptively inpaints missing depth values to render complete novel views.
  arXiv  Detail & Related papers  (2022-04-22T03:17:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.