Zhongang Cai

caizhongang's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 18 days ago

Scaling Spatial Intelligence with Multimodal Foundation Models

Paper • 2511.13719 • Published 22 days ago • 44

authored 6 papers 4 months ago

Large Motion Model for Unified Multi-Modal Motion Generation

Paper • 2404.01284 • Published Apr 1, 2024

SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation

Paper • 2501.09782 • Published Jan 16

Deblur-Avatar: Animatable Avatars from Motion-Blurred Monocular Videos

Paper • 2501.13335 • Published Jan 23

Controllable Human-centric Keyframe Interpolation with Generative Prior

Paper • 2506.03119 • Published Jun 3 • 2

DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

Paper • 2508.00599 • Published Aug 1 • 7

Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

Paper • 2508.13142 • Published Aug 18 • 34

authored a paper 9 months ago

EgoLife: Towards Egocentric Life Assistant

Paper • 2503.03803 • Published Mar 5 • 46

authored a paper 10 months ago

WHAC: World-grounded Humans and Cameras

Paper • 2403.12959 • Published Mar 19, 2024 • 4

authored 11 papers about 1 year ago

Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction

Paper • 2303.13796 • Published Mar 24, 2023 • 2

SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling

Paper • 2303.17368 • Published Mar 30, 2023

ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model

Paper • 2304.01116 • Published Apr 3, 2023 • 2

SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation

Paper • 2309.17448 • Published Sep 29, 2023 • 1

GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

Paper • 2311.14521 • Published Nov 24, 2023

DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering

Paper • 2307.10173 • Published Jul 19, 2023 • 6

IT3D: Improved Text-to-3D Generation with Explicit View Synthesis

Paper • 2308.11473 • Published Aug 22, 2023

AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

Paper • 2403.17934 • Published Mar 26, 2024

MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model

Paper • 2208.15001 • Published Aug 31, 2022

BiBench: Benchmarking and Analyzing Network Binarization

Paper • 2301.11233 • Published Jan 26, 2023

Playing for 3D Human Recovery

Paper • 2110.07588 • Published Oct 14, 2021