Stars
UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
Interactive Character Control with Auto-Regressive Motion Diffusion Models
Using ChatGPT to create AR experiences with natural language.
[SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig
Character Animation Diffusion with Any Topology
Official pytorch implementation of MotionLLaMA based on MMEngine
🔥🔥🔥 Set the world of 3D faces on fire with INFERNO 🔥🔥🔥
This is a implementation of the 3D FLAME model in PyTorch
[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"
A tools to estimate SMPL-X parameters (with T pose) from FLAME meshes (or FLAME parameters)
LLM大模型（重点）以及搜广推等 AI 算法中手写的面试题，（非 LeetCode），比如 Self-Attention, AUC等，一般比 LeetCode 更考察一个人的综合能力，又更贴近业务和基础知识一点
Official supplementary code for Mogo: RQ Hierarchical Causal Transformer for High-Quality 3D Human Motion Generation, an autoregressive model for long-range 3D motion synthesis.
🎞️ [NeurIPS'24] MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
[ECCV 2024] Towards High-Quality 3D Motion Transfer with Realistic Apparel Animation - MMDMC Dataset
Code for paper "Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction" (ECCV 2024)
Motion classes, based on Holden's code http://theorangeduck.com/page/deep-learning-framework-character-motion-synthesis-and-editing
VPoser: Variational Human Pose Prior
[NeurIPS 2023] Official implementation of the paper "Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset"