This is an official implementation of the CVPR2022 paper "Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots".

Overview

Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots

Blind2Unblind

Citing Blind2Unblind

@inproceedings{wang2022blind2unblind,
  title={Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots}, 
  author={Zejin Wang and Jiazheng Liu and Guoqing Li and Hua Han},
  booktitle={International Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2022}
}

Installation

The model is built in Python3.8.5, PyTorch 1.7.1 in Ubuntu 18.04 environment.

Data Preparation

1. Prepare Training Dataset

  • For processing ImageNet Validation, please run the command

    python ./dataset_tool.py
  • For processing SIDD Medium Dataset in raw-RGB, please run the command

    python ./dataset_tool_raw.py

2. Prepare Validation Dataset

​ Please put your dataset under the path: ./Blind2Unblind/data/validation.

Pretrained Models

The pre-trained models are placed in the folder: ./Blind2Unblind/pretrained_models

# # For synthetic denoising
# gauss25
./pretrained_models/g25_112f20_beta19.7.pth
# gauss5_50
./pretrained_models/g5-50_112rf20_beta19.4.pth
# poisson30
./pretrained_models/p30_112f20_beta19.1.pth
# poisson5_50
./pretrained_models/p5-50_112rf20_beta20.pth

# # For raw-RGB denoising
./pretrained_models/rawRGB_112rf20_beta19.4.pth

# # For fluorescence microscopy denooising
# Confocal_FISH
./pretrained_models/Confocal_FISH_112rf20_beta20.pth
# Confocal_MICE
./pretrained_models/Confocal_MICE_112rf20_beta19.7.pth
# TwoPhoton_MICE
./pretrained_models/TwoPhoton_MICE_112rf20_beta20.pth

Train

  • Train on synthetic dataset
python train_b2u.py --noisetype gauss25 --data_dir ./data/train/Imagenet_val --val_dirs ./data/validation --save_model_path ../experiments/results --log_name b2u_unet_gauss25_112rf20 --Lambda1 1.0 --Lambda2 2.0 --increase_ratio 20.0
  • Train on SIDD raw-RGB Medium dataset
python train_sidd_b2u.py --data_dir ./data/train/SIDD_Medium_Raw_noisy_sub512 --val_dirs ./data/validation --save_model_path ../experiments/results --log_name b2u_unet_raw_112rf20 --Lambda1 1.0 --Lambda2 2.0 --increase_ratio 20.0
  • Train on FMDD dataset
python train_fmdd_b2u.py --data_dir ./dataset/fmdd_sub/train --val_dirs ./dataset/fmdd_sub/validation --subfold Confocal_FISH --save_model_path ../experiments/fmdd --log_name Confocal_FISH_b2u_unet_fmdd_112rf20 --Lambda1 1.0 --Lambda2 2.0 --increase_ratio 20.0

Test

  • Test on Kodak, BSD300 and Set14

    • For noisetype: gauss25

      python test_b2u.py --noisetype gauss25 --checkpoint ./pretrained_models/g25_112f20_beta19.7.pth --test_dirs ./data/validation --save_test_path ./test --log_name b2u_unet_g25_112rf20 --beta 19.7
    • For noisetype: gauss5_50

      python test_b2u.py --noisetype gauss5_50 --checkpoint ./pretrained_models/g5-50_112rf20_beta19.4.pth --test_dirs ./data/validation --save_test_path ./test --log_name b2u_unet_g5_50_112rf20 --beta 19.4
    • For noisetype: poisson30

      python test_b2u.py --noisetype poisson30 --checkpoint ./pretrained_models/p30_112f20_beta19.1.pth --test_dirs ./data/validation --save_test_path ./test --log_name b2u_unet_p30_112rf20 --beta 19.1
    • For noisetype: poisson5_50

      python test_b2u.py --noisetype poisson5_50 --checkpoint ./pretrained_models/p5-50_112rf20_beta20.pth --test_dirs ./data/validation --save_test_path ./test --log_name b2u_unet_p5_50_112rf20 --beta 20.0
  • Test on SIDD Validation in raw-RGB space

python test_sidd_b2u.py --checkpoint ./pretrained_models/rawRGB_112rf20_beta19.4.pth --test_dirs ./data/validation --save_test_path ./test --log_name validation_b2u_unet_raw_112rf20 --beta 19.4
  • Test on SIDD Benchmark in raw-RGB space
python benchmark_sidd_b2u.py --checkpoint ./pretrained_models/rawRGB_112rf20_beta19.4.pth --test_dirs ./data/validation --save_test_path ./test --log_name benchmark_b2u_unet_raw_112rf20 --beta 19.4
  • Test on FMDD Validation

    • For Confocal_FISH
    python test_fmdd_b2u.py --checkpoint ./pretrained_models/Confocal_FISH_112rf20_beta20.pth --test_dirs ./dataset/fmdd_sub/validation --subfold Confocal_FISH --save_test_path ./test --log_name Confocal_FISH_b2u_unet_fmdd_112rf20 --beta 20.0
    • For Confocal_MICE
    python test_fmdd_b2u.py --checkpoint ./pretrained_models/Confocal_MICE_112rf20_beta19.7.pth --test_dirs ./dataset/fmdd_sub/validation --subfold Confocal_MICE --save_test_path ./test --log_name Confocal_MICE_b2u_unet_fmdd_112rf20 --beta 19.7
    • For TwoPhoton_MICE
    python test_fmdd_b2u.py --checkpoint ./pretrained_models/TwoPhoton_MICE_112rf20_beta20.pth --test_dirs ./dataset/fmdd_sub/validation --subfold TwoPhoton_MICE --save_test_path ./test --log_name TwoPhoton_MICE_b2u_unet_fmdd_112rf20 --beta 20.0
You might also like...
TCTrack: Temporal Contexts for Aerial Tracking (CVPR2022)
TCTrack: Temporal Contexts for Aerial Tracking (CVPR2022)

TCTrack: Temporal Contexts for Aerial Tracking (CVPR2022) Ziang Cao and Ziyuan Huang and Liang Pan and Shiwei Zhang and Ziwei Liu and Changhong Fu In

Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding (CVPR2022)
Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding (CVPR2022)

Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding by Qiaole Dong*, Chenjie Cao*, Yanwei Fu Paper and Supple

FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset (CVPR2022)
FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset (CVPR2022)

FaceVerse FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset Lizhen Wang, Zhiyuan Chen, Tao Yu, Chenguang

 Towards Implicit Text-Guided 3D Shape Generation (CVPR2022)
Towards Implicit Text-Guided 3D Shape Generation (CVPR2022)

Towards Implicit Text-Guided 3D Shape Generation Towards Implicit Text-Guided 3D Shape Generation (CVPR2022) Code for the paper [Towards Implicit Text

Video Frame Interpolation with Transformer (CVPR2022)

VFIformer Official PyTorch implementation of our CVPR2022 paper Video Frame Interpolation with Transformer Dependencies python = 3.8 pytorch = 1.8.0

[CVPR2022] Representation Compensation Networks for Continual Semantic Segmentation
[CVPR2022] Representation Compensation Networks for Continual Semantic Segmentation

RCIL [CVPR2022] Representation Compensation Networks for Continual Semantic Segmentation Chang-Bin Zhang1, Jia-Wen Xiao1, Xialei Liu1, Ying-Cong Chen2

A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution (CVPR2022)
A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution (CVPR2022)

A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution (CVPR2022) https://arxiv.org/abs/2203.09388 Jianqi Ma, Zheto

Unsupervised Domain Adaptation for Nighttime Aerial Tracking (CVPR2022)
Unsupervised Domain Adaptation for Nighttime Aerial Tracking (CVPR2022)

Unsupervised Domain Adaptation for Nighttime Aerial Tracking (CVPR2022) Junjie Ye, Changhong Fu, Guangze Zheng, Danda Pani Paudel, and Guang Chen. Uns

CVPR2022 (Oral) - Rethinking Semantic Segmentation: A Prototype View
CVPR2022 (Oral) - Rethinking Semantic Segmentation: A Prototype View

Rethinking Semantic Segmentation: A Prototype View Rethinking Semantic Segmentation: A Prototype View, Tianfei Zhou, Wenguan Wang, Ender Konukoglu and

Comments
  • How to prepare ValidationNoisyBlocksRaw.mat for SIDD RAW training?

    How to prepare ValidationNoisyBlocksRaw.mat for SIDD RAW training?

    Thank you for the great work but can you please provide some code/pointer on how to prepare ValidationNoisyBlocksRaw.mat which is required for validation for SIDD RAW denoising?

    opened by wind-surfer 1
  • Pretrained Models

    Pretrained Models

    This work is amazing and I can't wait to use it, but I haven't had time to train the model lately, so I was wondering if you could release your pre-trained model?

    opened by Volodymyr233 1
Owner
demonsjin
Ph.D Candidate
demonsjin
Official code for CVPR2022 paper: Depth-Aware Generative Adversarial Network for Talking Head Video Generation

?? Depth-Aware Generative Adversarial Network for Talking Head Video Generation (CVPR 2022) ?? If DaGAN is helpful in your photos/projects, please hel

Fa-Ting Hong 474 Dec 2, 2022
Official code for "Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes", CVPR2022

[CVPR 2022] Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes Dongkwon Jin, Wonhui Park, Seong-Gyun Jeong, Heeyeon Kwon, and Cha

Dongkwon Jin 103 Nov 13, 2022
Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

E2FGVI (CVPR 2022) English | 简体中文 This repository contains the official implementation of the following paper: Towards An End-to-End Framework for Flo

Media Computing Group @ Nankai University 515 Dec 5, 2022
Code for the CVPR2022 paper "Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity"

Introduction This is an official release of the paper "Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity" (arxiv link). Abstrac

Leo 21 Nov 23, 2022
CVPR2022 paper "Dense Learning based Semi-Supervised Object Detection"

[CVPR2022] DSL: Dense Learning based Semi-Supervised Object Detection DSL is the first work on Anchor-Free detector for Semi-Supervised Object Detecti

Bhchen 70 Nov 30, 2022
Source code for CVPR2022 paper "Abandoning the Bayer-Filter to See in the Dark"

Abandoning the Bayer-Filter to See in the Dark (CVPR 2022) Paper: https://arxiv.org/abs/2203.04042 (Arxiv version) This code includes the training and

null 70 Nov 11, 2022
PSTR: End-to-End One-Step Person Search With Transformers (CVPR2022)

PSTR (CVPR2022) This code is an official implementation of "PSTR: End-to-End One-Step Person Search With Transformers (CVPR2022)". End-to-end one-step

Jiale Cao 25 Nov 22, 2022
[CVPR2022] Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos

Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos Created by Muheng Li, Lei Chen, Yueqi Duan, Zhilan Hu, Jianjiang Feng, Jie

null 56 Nov 22, 2022
Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022)

Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022) By Shilong Zhang*, Zhuoran Yu*, Liyang Liu*, Xinjiang Wang, Aojun Zhou,

Shilong Zhang 126 Nov 29, 2022
Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis (CVPR2022)

Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis Multi-View Consistent Generative Adversarial Networks for 3D-aware

Xuanmeng Zhang 76 Nov 21, 2022