GUSH3R: Everyone Everywhere All at Once as Gaussians
2026-07-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present GUSH3R, a new method to reconstruct both moving people and static backgrounds from single-camera videos in real time. Unlike previous methods that often produce rough shapes or can't handle moving humans well, their approach uses 3D Gaussian Splatting to create detailed 3D scenes all at once. Their experiments show this method produces good-quality new views of the scenes faster than older, slower techniques that rely on optimization. This makes it useful for applications needing quick and realistic 3D scene reconstruction.
monocular video3D reconstructiondynamic humansscene geometrycamera motion3D Gaussian Splattingnovel view synthesisfeed-forward methodsnon-rigid objectsphotorealistic rendering
Authors
Keito Abe, Kaede Shiohara, Takashi Otonari, Toshihiko Yamasaki
Abstract
Reconstructing dynamic human-scene environments from monocular videos is a challenging problem that requires jointly modeling scene geometry, camera motion, and non-rigid human dynamics while enabling photorealistic rendering. Recent feed-forward methods can efficiently predict geometry, but they are often limited to non-photorealistic representations such as point clouds and meshes, or they fail to handle non-rigid objects, particularly dynamic humans. To fill this gap, we present GUSH3R (Gaussian-Unified Scene Human 3D Reconstruction), a feed-forward framework for online dynamic human-scene reconstruction. From a monocular human-scene video, our method reconstructs dynamic humans (everyone) and static scenes (everywhere) in a single forward pass (all at once) as 3D Gaussian Splatting (3DGS) primitives (as gaussians), which are geometrically consistent and capable of novel view synthesis. Experiments on monocular human-scene datasets demonstrate that our approach achieves competitive novel view synthesis quality while significantly improving inference efficiency compared to optimization-based methods.