Yuzhi ZHAO

deepfillv2. The PyTorch implementation of ICCV 2019 oral paper: free-form inpainting (deepfillv2), especially Gated Conv

Hierarchical-Regression-Network-for-Spectral-Reconstruction-from-RGB-Images. CVPR NTIRE 2020 Spectral Reconstruction Challenge 1st Place Paper

D2HNet. D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration. ECCV, 2022

ChildPredictor. ChildPredictor: A Child Face Prediction Framework with Disentangled Learning. IEEE TMM, 2022

Semantic-Colorization-GAN. SCGAN: Saliency-map Guided Colorization with Generative Adversarial Network. IEEE TCSVT, 2020

A-New-Convolutional-Neural-Network-Based-Data-Driven-Fault-Diagnosis-Method. TensorFlow implementation of a CNN based mechanical science paper

Self-Guided-Network-for-Fast-Image-Denoising. The PyTorch implementation of ICCV 2019 paper SGN

Deep-Convolutional-Network-Cascade-for-Facial-Point-Detection. TensorFlow implementation of cascade CNN, trained level-by-level

PyTorch-Special-Pre-trained-Models. Special pre-trained VGG-16 / ResNet-50 network on CIE Lab and Grayscale images

VCGAN. VCGAN: Video Colorization with Hybrid Generative Adversarial Network. IEEE TMM, 2022

QRNet. Modeling Dual-Exposure Quad-Bayer Patterns for Joint Denoising and Deblurring. IEEE TIP, 2024

PyTorch-Sobel. Sobel operator-based loss functions and operation

RAW2RGB-GAN. PyTorch implementation of saliency map-aided GAN for Auto-demosaic+denosing

HSGAN. HSGAN: Hyperspectral Reconstruction from RGB Images with Generative Adversarial Network. IEEE TNNLS, 2023

PyTorch-Useful-Codes. Some Blocks and Networks implemented by PyTorch

DeblurGANv2-MobileNetv123-PyTorch. Provide pre-trained MobileNetv123 and MobileNet-DSC FPN models for DeblurGANv2

Reference-Based-Sketch-Image-Colorization-ImageNet. PyTorch implementation of CVPR 2020 paper (Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence) and pre-trained model on ImageNet dataset

SVCNet. SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation. IEEE TIP, 2023

PyTorch-MobileNet-v123. Provide implementations and pre-trained models of MobileNet-v1, v2, and v3

ICM-Assistant. ICM-Assistant: Instruction-tuning Multimodal Large Language Models for Rule-based Explainable Image Content Moderation. AAAI, 2025

Legacy-Photo-Editing-with-Learned-Noise-Prior. The github page for WACV 2021 paper: Legacy Photo Editing with Learned Noise Prior

Animal-Face-Detectors. The face detectors for human, cat, dog using dlib and opencv

Infrared-Image-Colorization. A research project on infrared image colorization using PyTorch

Non-Local-Block-PyTorch. Self Attention techniques commonly used in GAN based applications

Learning-Blind-Video-Temporal-Consistency-with-PWCNet. Re-implementation of ECCV'18 paper to smooth videos

PyTorch-Domain-Transfer-GAN. The re-implementation of diverse domain transfer methods

PyTorch-MobileNet-v123-InstanceNorm. PyTorch-MobileNet-v123-InstanceNorm with pre-trained models

KG-RAG-GUI-Agent. KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generation, EMNLP 2025

DSWN. Implementation of our sRGB denoising method in CVPR 2020 NTIRE Workshop

Visualization-GAN-ability. Different GAN codes working on MNIST database

KPN-Single-Image. kernel prediction network works for single image denoising

Camera-Demosaic. Some functions for demosaicking camera RAW files including .raw / .NEF format

SIDD-benchmark. Users can freely try their models on the SIDD dataset based on this code

Auto-Crop-Videos-and-Blur-Modelling. Automatic crop videos and produce static, interpolation, and averaged frames or new videos for making blur dataset

Edge-Aware-Multi-Scale-Progressive-Colorization. Python

nerf-pytorch. A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

Context-Encoder. Modified context encoder PyTorch implementation

MSGAN-Pix2Pix-Colorization. Pix2Pix framework for colorization; MSGAN is utilized to build multiple results

PerceptualSimilarity. Learned Perceptual Image Patch Similarity (LPIPS) metric. In CVPR, 2018.

Deep-Network-Interpolation-DNI. CVPR19 - Deep Network Interpolation for Continuous Imagery Effect Transition

DeblurGANv1. PyTorch implementation of CVPR 2018 paper: DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks