Stars
StyleGAN-Human: A Data-Centric Odyssey of Human Generation
MAT: Mask-Aware Transformer for Large Hole Image Inpainting
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"
Face analysis tools for modern research, equipped with state-of-the-art Face Parsing and Face Alignment
The human face subset of LAION-400M for large-scale face pretraining.
FaRL for Facial Representation Learning [Official, CVPR 2022]
An open source implementation of CLIP.
(CVPR 2022) HairMapper: Removing Hair from Portraits Using GANs.
Official Pytorch implementation of "Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment (ECCV 2022)"
🌕 [BMVC 2022] You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction. SOTA for low light enhancement, 0.004 seconds try this for pre-p…
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
[ICCV 2023] HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending
StyleGAN2-ADA - Official PyTorch implementation
Robust Human Matting via Semantic Guidance, ACCV 2022.
Official Pytorch implementation of 'RoI Tanh-polar Transformer Network for Face Parsing in the Wild.'
State-of-the-art 2D and 3D Face Analysis Project
Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch
A library to scrap google images
Barbershop: GAN-based Image Compositing using Segmentation Masks (SIGGRAPH Asia 2021)
Implementation of TAAConvLSTM and SAAConvLSTM used in "Attention Augmented ConvLSTM for Environment Prediction"
Code and models accompanying "Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning"
Teams can post their projects here.
Navigator, our self-driving vehicle software stack
Implementation of occupancy grid predictions via ConvLSTM video frame prediction architecture.