[ECCV 2024] MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model.

Stable-Hair: Real-World Hair Transfer via Diffusion Model

Native WebRTC uses v4l2 hardware h264 and software openh264 encoder for live streaming on Raspberry Pi.

Bring portraits to life!

[CVPR 2023] Official implementation of the paper "One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer"

Official codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

GUI for visualization and interactive editing of SMPL-family body models ie. SMPL, SMPL-X, MANO, FLAME.

High-resolution models for human tasks.

[ECCV 2024, Oral] UGG: Unified Generative Grasping

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Gaussian Splatting from VGGSfM and Mast3r, and their comparison

Modified 3D Gaussian rasterizer for latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

[3DV 2024] Official repo of "TeCH: Text-guided Reconstruction of Lifelike Clothed Humans"

Modern OpenGL binding for Python

Headless 3D rendering with python

Project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning"

Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality

Official Repo of Graphist

Official Implementation of Posterior Distillation Sampling

[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"

A Python framework for high performance GPU simulation and graphics

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion

Powerful yet simple to use screenshot software 🖥️ 📸

The Training and Demo code for: Ash: Animatable gaussian splats for efficient and photoreal human rendering (CVPR 2024)