Li-ChengYan
Follow
Stars
WiLoR: End-to-end 3D hand localization and reconstruction in-the-wild
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
PyTorch code and models for the DINOv2 self-supervised learning method.
Robust Speech Recognition via Large-Scale Weak Supervision
Flexible audio loudness meter in Python with implementation of ITU-R BS.1770-4 loudness algorithm
Official implementations for paper: Anydoor: zero-shot object-level image customization
Official Implementation of paper "Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence"
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.
Lightweight Lenovo Vantage and Hotkeys replacement for Lenovo Legion laptops.
[ECCV 2024] Official implementation of the paper "X-Pose: Detecting Any Keypoints"
A simple face detect and alignment method, which is easy and stable.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Pytorch implementation of paper "One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing"
Code of ”Comprehensive Competition Mechanism in Palmprint Recognition“ (Accepted by IEEE TIFS)
MagicEdit: High-Fidelity Temporally Coherent Video Editing
A discriminative object placement approach
RAST 1.0: Restorable Arbitrary Style Transfer via Multi-restoration
The official code of our ICCV2023 work: Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation
This project aims to extract ROI like finger tip, Palmprint and Hand-geometry from a single hand image.
📖 A curated list of resources dedicated to talking face.
A repo for training and finetuning models for hands segmentation.
A curated list of papers, code and resources pertaining to image composition/compositing or object insertion/addition/compositing, which aims to generate realistic composite image.
Paint by Example: Exemplar-based Image Editing with Diffusion Models
SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.