| Download | - View final version: SHARE: Scene-Human Aligned Reconstruction (PDF, 7.5 MiB)
|
|---|
| DOI | Resolve DOI: https://doi.org/10.1145/3757376.3771393 |
|---|
| Author | Search for: Li, Joshua1ORCID identifier: https://orcid.org/0009-0007-4618-6815; Search for: Chharawala, Brendan1ORCID identifier: https://orcid.org/0009-0005-1512-4895; Search for: Shu, Chang2ORCID identifier: https://orcid.org/0000-0001-6331-0522; Search for: Peng, Xue Bin3ORCID identifier: https://orcid.org/0000-0002-3677-5655; Search for: Xi, Pengcheng2ORCID identifier: https://orcid.org/0000-0003-3236-5234 |
|---|
| Affiliation | - University of Waterloo
- National Research Council Canada. Digital Technologies
- Simon Fraser University
|
|---|
| Format | Text, Article |
|---|
| Conference | SA Technical Communications '25: SIGGRAPH Asia 2025 Technical Communications, December 15-18, 2025, Hong Kong |
|---|
| Abstract | Animating realistic character interactions with the surrounding environment is important for autonomous agents in gaming, AR/VR, and robotics. However, current methods for human motion reconstruction struggle with accurately placing humans in 3D space. We introduce Scene-Human Aligned REconstruction (SHARE), a technique that leverages the scene geometry’s inherent spatial cues to accurately ground human motion reconstruction. Each reconstruction relies solely on a monocular RGB video from a stationary camera. SHARE first estimates a human mesh and segmentation mask for every frame, alongside a scene point map at keyframes. It iteratively refines the human’s positions at these keyframes by comparing the human mesh against the human point map extracted from the scene using the mask. Crucially, we also ensure that non-keyframe human meshes remain consistent by preserving their relative root joint positions to keyframe root joints during optimization. Our approach enables more accurate 3D human placement while reconstructing the surrounding scene, facilitating use cases on both curated datasets and in-the-wild web videos. Extensive experiments demonstrate that SHARE outperforms existing methods. |
|---|
| Publication date | 2025-12-14 |
|---|
| Publisher | Association for Computing Machinery |
|---|
| Copyright statement | |
|---|
| Licence | |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | e49348d1-17d6-4f1c-8fa6-d1fde50b3b6d |
|---|
| Record created | 2026-02-23 |
|---|
| Record modified | 2026-03-18 |
|---|
