Stars
[CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…
[ICCV 2025] This repo is an official PyTorch implementation of PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Image.
A PyTorch native platform for training generative AI models
IDOL: Instant Photorealistic 3D Human Creation from a Single Image. An open-source project for fast, high-fidelity, and generalizable 3D human reconstruction from a single image.
Make your wildest 3D ConvNet dream architectures come true
AniCrafter: Customizing Realistic Human-Centric Animation via Avatar-Background Conditioning in Video Diffusion Models
Official project page of MTVCrafter, a new paradigm for animating arbitrary characters with 4D motion tokens.
Official implementation of "En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data", CVPR 2024; 3D Avatar Generation and Animation
Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"
Some simple Blender scripts for rendering paper figures
Official Repository of Recovering Dynamic 3D Sketches from Videos (CVPR 2025)
[Official Implementation] Subject-driven Video Generation via Disentangled Identity and Motion
[NeurIPS 2025] GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
SkyReels V1: The first and most advanced open-source human-centric video foundation model
[ICCV2025] LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
[TIP 2025] From Parts to Whole: A Unified Reference Framework for Controllable Human Image Generation
Official Repository for "Diffusion HPC: Generate Synthetic Data for Human Mesh Recovery in Challenging Domains" (3DV 2024 Spotlight)
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
ComfyUI TRELLIS is a large 3D asset generation in various formats, such as Radiance Fields, 3D Gaussians, and meshes. The cornerstone of TRELLIS is a unified Structured LATent (SLAT) representation…
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos
[ICCV 2025] Official impl. of "MV-Adapter: Multi-view Consistent Image Generation Made Easy"