soonwonh
Follow
Stars
The official implementation of HierSpeech++
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
The source code of "DINet: deformation inpainting network for realistic face visually dubbing on high resolution video."
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.
PyTorch implementation of "StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator"
꼼꼼한 딥러닝 논문 리뷰와 코드 실습
Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)
A PyTorch implementation of the Transformer model in "Attention is All You Need".
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Denoising Diffusion Probabilistic Models
A collection of literature after or concurrent with Masked Autoencoder (MAE) (Kaiming He el al.).
Collecting papers about new view synthesis
Official Code for DragGAN (SIGGRAPH 2023)
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
A latent text-to-image diffusion model
CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer Arxiv - HAT: Hybrid Attention Transformer for Image Restoration
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code
本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形，设置面部区域可配置的增强方式进行合成唇形（人脸）区域画面增强，提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧，补充帧间合成唇形的动作过渡，使合成的唇形更为流畅、真实以及自然。
Pytorch implementation of paper "One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing"
[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.