Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation
- 29 August 2026
- journal article
- research article
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (9) , 414
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- National Key R&D Program of China (2023YFC3082100)
- the Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems (VRLAB2026C04)
- Science Fund for Distinguished Young Scholars of Tianjin Municipality (22JCJQJC00040)
This publication has 35 references indexed in Scilit:
- MUSt3R: Multi-view Network for Stereo 3D Reconstruction2025
- Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors2025
- Continuous 3D Perception Model with Persistent State2025
- VGGT: Visual Geometry Grounded Transformer2025
- Grounding Image Matching in 3D with MASt3R2024
- Multi-HMR: Multi-person Whole-Body Human Mesh Recovery in a Single Shot2024
- Synergistic Global-Space Camera and Human Reconstruction from Videos2024
- VoxelPose: Towards Multi-camera 3D Human Pose Estimation in Wild Environment2020
- End-to-end Dynamic Matching Network for Multi-view Multi-person 3D Pose Estimation2020
- Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image2016