adityac8

pixel2style2pixel

Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework

koila

Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code.

mdetr

Focal-Transformer

[NeurIPS 2021 Spotlight] Official code for "Focal Self-attention for Local-Global Interactions in Vision Transformers"

CoTNet

This is an official implementation for "Contextual Transformer Networks for Visual Recognition".

pidinet

Code for the ICCV 2021 paper "Pixel Difference Networks for Efficient Edge Detection" (Oral).

pytorch-cosine-annealing-with-warmup

HINet

segformer-pytorch

Implementation of Segformer, Attention + MLP neural network for segmentation, in Pytorch

pytorch-distributed-training

Simple tutorials on Pytorch DDP training

FNet-pytorch

Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms

SMSR

[CVPR 2021] Exploring Sparsity in Image Super-Resolution for Efficient Inference

OW-DETR

[CVPR 2022] Official Pytorch code for OW-DETR: Open-world Detection Transformer

ddfnet

The official implementation of the CVPR2021 paper: Decoupled Dynamic Filter Networks

ELAN

[ECCV2022] Efficient Long-Range Attention Network for Image Super-resolution

automatic-integration

Official repo for AutoInt: Automatic Integration for Fast Neural Volume Rendering in CVPR 2021

RainNet

[CVPR 2021] Region-aware Adaptive Instance Normalization for Image Harmonization

DCLGAN

Code for Dual Contrastive Learning for Unsupervised Image-to-Image Translation, NTIRE, CVPRW 2021, oral.

CAT

Official implement of "CAT: Cross Attention in Vision Transformer".

DAPN

A pytorch implementation of "Domain-Adaptive Few-Shot Learning"

ImageProcessingTransformer

Third party Pytorch implement of Image Processing Transformer (Pre-Trained Image Processing Transformer arXiv:2012.00364v2)

VRGNet

【CVPR 2021, Variational Rain Generator】 From Rain Generation to Rain Removal

BiAM

[ICCV 2021] Official Pytorch implementation for Discriminative Region-based Multi-Label Zero-Shot Learning SOTA results on NUS-WIDE and OpenImages

A-Hierarchical-Transformation-Discriminating-Generative-Model-for-Few-Shot-Anomaly-Detection

Official pytorch implementation of the paper: "A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection"

multi-task-defocus-deblurring-dual-pixel-nimat

Reference github repository for the paper "Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning". We propose a single-image deblurring network that incorporates the two sub-aperture views into a multitask framework. Specifically, we show that jointly learning to predict the two DP views from a single blurry input image improves the network’s ability to learn to deblur the image. Our experiments show this multi-task strategy achieves +1dB PSNR improvement over state-of-the-art defocus deblurring methods. In addition, our multi-task framework allows accurate DP-view synthesis (e.g., ~ 39dB PSNR) from the single input image. These high-quality DP views can be used for other DP-based applications, such as reflection removal. As part of this effort, we have captured a new dataset of 7,059 high-quality images to support our training for the DP-view synthesis task.

AFFT

Code for the paper: Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation.

REVIDE_Dataset

The first REal-world VIdeo DEhazing dataset(REVIDE).

colour_transfer_MKL

Python implementation of colour transfer algorithm based on linear Monge-Kantorovitch solution

SWAL

Selective Wavelet Attention Learning for Single Image Deraining

PerTeRNet

Image Enhancement via Associated Perturbation Removal and Texture Reconstruction Learning