azuredsky's repositories
Background-Matting
Background Matting: The World is Your Green Screen
AA-TransUNet
The repository for paper AA-TransUNet: Attention Augmented TransUNet For Nowcasting Tasks.
audio2photoreal
Code and dataset for photorealistic Codec Avatars driven from audio
Awesome-Human-Body-Video-Generation
A work list of recent human body video generation method. This repository focus on half/full body human body video generation method, The Nerf, Gaussian splashing, Motion Pose, and talking head/Portrait is not included.
Chinese-CLIP
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
chinese_speech_pretrain
chinese speech pretrained models
contextual_loss_pytorch
Contextual Loss (CX) and Contextual Bilateral Loss (CoBi).
DCT-Net
Official implementation of "DCT-Net: Domain-Calibrated Translation for Portrait Stylization", SIGGRAPH 2022 (TOG); Multi-style cartoonization
DL-Demos
Demos for deep learning
FBA-Matting
Official repository for the paper F, B, Alpha Matting
Fengshenbang-LM
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。
FGT
[ECCV 2022] Flow-Guided Transformer for Video Inpainting
HR-VITON
Official PyTorch implementation for the paper High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions (ECCV 2022).
HRFAE
Official implementation for paper High Resolution Face Age Editing
indexnet_matting
Indices Matter: Learning to Index for Deep Image Matting
learnopencv
Learn OpenCV : C++ and Python Examples
Make-Your-Anchor
[CVPR 2024] Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework.
ManiTalk
manipulable audio-driven talking head generation system
NanoTrack
Deep learning-based mobile model deployment(Object Tracking). Lightweight Object Tracking, NCNN,
PIPNet
Efficient facial landmark detector
QA-CLIP
Chinese CLIP models with SOTA performance.
SADMA
SADMA: SAtellite baseD MArine debris detection
talking-face-arxiv-daily
🎓 Update Talking-Face Research Papers Daily, Now Integrated with LLM Analysis.
talking_face_preprocessing
Preprocessing Scipts for Talking Face Generation
temporal-shift-module
[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
vit-vqvae
VQ-VAE implementation using Vision Transformers for both the encoder and decoder
Wav2Lip-GFPGAN
High quality Lip sync