Invited Posters
@CVPR 2024, Seattle, USA
June 17th, 2024
@CVPR 2024, Seattle, USA
June 17th, 2024
EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild [Project Page]
2. Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera [Project Page]
3. OSX: One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer [Project Page]
4. ScoreHMR: Score-Guided Diffusion for 3D Human Recovery [Project Page]
5. Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation [Project Page]
6. MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervision [ArXiv]
7. DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery [Project Page]
8. CLOAF: CoLlisiOn-Aware Human Flow [ArXiv]
9. LEMON: Learning 3D Human-Object Interaction Relation from 2D Images [Project Page]
10. I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions [Project Page]
11. GRIP: Generating Interaction Poses Using Spatial Cues and Latent Consistency [Project Page]
12. Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation [Project Page]
13. GenZI: Zero-Shot 3D Human-Scene Interaction Generation [Project Page]
14. TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation [Project Page]
15. WANDR: Intention-guided Human Motion Generation [Project Page]
16. EgoGen: An Egocentric Synthetic Data Generator [Project Page]
17. Scaling Up Dynamic Human-Scene Interaction Modeling [Project Page]
18. AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation [Project Page]
19. Generative Proxemics: A Prior for 3D Social Interaction from Images [Project Page]
20. WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion [Project Page]
21. Hi4D: 4D Instance Segmentation of Close Human Interaction [Project Page]
22. Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot [Project Page]
23. PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos [ArXiv]