| Téléchargement | - Voir la version finale : SHARE: Scene-Human Aligned Reconstruction (PDF, 7.5 Mio)
|
|---|
| DOI | Trouver le DOI : https://doi.org/10.1145/3757376.3771393 |
|---|
| Auteur | Rechercher : Li, Joshua1Identifiant ORCID : https://orcid.org/0009-0007-4618-6815; Rechercher : Chharawala, Brendan1Identifiant ORCID : https://orcid.org/0009-0005-1512-4895; Rechercher : Shu, Chang2Identifiant ORCID : https://orcid.org/0000-0001-6331-0522; Rechercher : Peng, Xue Bin3Identifiant ORCID : https://orcid.org/0000-0002-3677-5655; Rechercher : Xi, Pengcheng2Identifiant ORCID : https://orcid.org/0000-0003-3236-5234 |
|---|
| Affiliation | - University of Waterloo
- Conseil national de recherches Canada. Technologies numériques
- Simon Fraser University
|
|---|
| Format | Texte, Article |
|---|
| Conférence | SA Technical Communications '25: SIGGRAPH Asia 2025 Technical Communications, December 15-18, 2025, Hong Kong |
|---|
| Résumé | 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. |
|---|
| Date de publication | 2025-12-14 |
|---|
| Maison d’édition | Association for Computing Machinery |
|---|
| Déclaration de droit d’auteur | |
|---|
| Licence | |
|---|
| Dans | |
|---|
| Langue | anglais |
|---|
| Publications évaluées par des pairs | Oui |
|---|
| Exporter la notice | Exporter en format RIS |
|---|
| Signaler une correction | Signaler une correction (s'ouvre dans un nouvel onglet) |
|---|
| Identificateur de l’enregistrement | e49348d1-17d6-4f1c-8fa6-d1fde50b3b6d |
|---|
| Enregistrement créé | 2026-02-23 |
|---|
| Enregistrement modifié | 2026-03-18 |
|---|
