End-to-End Speech Processing Toolkit

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

📚 A collection of Deep Learning based Image Colorization and Video Colorization papers.

A Collection of Papers and Codes in CVPR2022 about low level vision

StyTr2 : Image Style Transfer with Transformers

official project page of the paper "DeepChange: A Long-term Person Re-identification Benchmark"

[ICCV 2021] Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation

Official PyTorch implementation of Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks (ICLR 2022).

Official implementation of the paper GLU-Net (CVPR2020-Oral)

Ensembling Off-the-shelf Models for GAN Training

Revisiting RCAN: Improved Training for Image Super-Resolution

Contextual Loss (CX) and Contextual Bilateral Loss (CoBi).

Code for "Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose"

Occlusion robust 3D face reconstruction model in CFR-GAN (WACV 2022)

[Pre-print'22] Unofficial repository for "MAXIM: Multi-Axis MLP for Image Processing". SOTA for denoising, deblurring, deraining, dehazing, and low-light enhancement.

Learning to Caricature via Semantic Shape Transformation, IJCV 2021

SCL-LLE code

A sketch extractor for anime/illustration.

DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)

The source code of the ICCV2021 paper "PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering"

[CVPR 2019, Oral] "Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images" by Wuyang Chen*, Ziyu Jiang*, Zhangyang Wang, Kexin Cui, and Xiaoning Qian

AlignSeg: Feature-Aligned Segmentation Networks (TPAMI 2021)

Official implementation of "Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis"(WACV 2022/CVPRW 2021)