Zhengdi Yu

🔥(CVPR 2025 Highlight) Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera

(ECCV 2024) SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark

🔥(CVPR 2023) ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction

No description provided.

[CVPR2025] Hand-held Object Reconstruction from RGB Video with Dynamic Interaction

No description provided.

No description provided.

P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching

RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds

Personal website for Zhengdi Yu

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

[CVPR 2025] InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation

[CVPR 2025] InteractVLM: 3D Interaction Reasoning from 2D Foundational Models

[ArXiv 2025] This repo is official PyTorch implementation of the paper "Learning Dense Hand Contact Estimation from Imbalanced Data".

No description provided.

Text to pose model for sign language pose generation from a text sequence

1

No description provided.

HaMeR: Reconstructing Hands in 3D with Transformers

A generative world for general-purpose robotics & embodied AI learning.

collect papers about human motion capture

Parallelized triangle mesh --> continuous signed distance field on CPU

TFDS data loaders for sign language datasets.

This is the codebase for SHOW in Generating Holistic 3D Human Motion from Speech [CVPR2023],

Official implementation for "Ham2Pose: Animating Sign Language Notation into Pose Sequences" [CVPR 2023]

Monocular, One-stage, Regression of Multiple 3D People, ROMP[ICCV21], BEV[CVPR22]

Interacting Two-Hand 3D Pose and Shape Reconstruction from Single Color Image (ICCV 2021)

ECON: Explicit Clothed humans Obtained from Normals (CVPR 2023)

Code for ICCV2021 paper PARE: Part Attention Regressor for 3D Human Body Estimation

The is an implementation of the AccurateACL paper.