A python library for self-supervised learning on images.

Refine high-quality datasets and visual AI models

[CVPR 2024] Prompt Highlighter: Interactive Control for Multi-Modal LLMs

[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

Segment-anything interactively in NeRF.

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Code for "Audio-Driven Co-Speech Gesture Video Generation" (NeurIPS 2022, Spotlight Presentation).

Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition

Code for paper 'EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model'

OpenXRLab Neural Radiance Field (NeRF) Toolbox and Benchmark

[ECCV 2022] Relighting4D: Neural Relightable Human from Videos

REALY: Rethinking the Evaluation of 3D Face Reconstruction (ECCV 2022)

[ECCV 2022] Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing

Official repo for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image (CVPR 2022).

MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]

[CVPR 2022] Code for "Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation"

👩🏼‍🦰😺[ECCV'22] Official PyTorch Implementation of Sem2NeRF: Converting Single-View Semantic Masks to NeRFs

A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.

Using modified BiSeNet for face parsing in PyTorch

Official repository for CVPR 2022 paper: I M Avatar: Implicit Morphable Head Avatars from Videos

Photometric optimization code for creating the FLAME texture space and other applications

Code for C2-Matching (CVPR2021). Paper: Robust Reference-based Super-Resolution via C2-Matching.

Code for Talk-to-Edit (ICCV2021). Paper: Talk-to-Edit: Fine-Grained Facial Editing via Dialog.

Code for Text2Human (SIGGRAPH 2022). Paper: Text2Human: Text-Driven Controllable Human Image Generation

A large-scale high-quality human dataset with rich multi-modal annotations

Code for Few-Shot Head Swapping in the Wild (CVPR 2022 Oral)

A high-fidelity 3D face reconstruction library from monocular RGB image(s)

MobileFaceSwap: A Lightweight Framework for Video Face Swapping (AAAI 2022)