Code and models for "Rethinking Deep Image Prior for Denoising" (ICCV 2021)

Last update: Dec 29, 2022

Related tags

Overview

DIP-denosing

This is a code repo for Rethinking Deep Image Prior for Denoising (ICCV 2021).

Addressing the relationship between Deep image prior and effective degrees of freedom, DIP-SURE with STE(stochestic temporal ensemble) shows reasonable result on single image denoising.

If you use any of this code, please cite the following publication:

@article{jo2021dipdenoising,
  author  = {Yeonsik Jo, Se young chun,  and Choi, Jonghyun},
  title     = {Rethinking Deep Image Prior for Denoising},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month     = {October},
  year      = {2021},
  pages     = {5087-5096}
}

Working environment

TITAN Xp
ubuntu 18.04.4
pytorch 1.6

Note: Experimental results were not checked in other environments.

Set-up

Make your own environment

conda create --name DIP --file requirements.txt
conda avtivate DIP
pip install tqdm

Inference

Produce CSet9 result

bash exp_denoising.sh CSet9 <GPU ID>

For your own data with sigma=25 setup

mkdir testset/<YOUR_DATASET>
python main.py --dip_type eSURE_new --net_type s2s --exp_tag <EXP_NAME> --optim RAdam --force_steplr --desc sigma25   denoising --sigma 25 --eval_data <YOUR_DATASET>

Browsing experimental result

We provide reporting code with invoke.

invoke showtable csv/<exp_type>/<exp_tag>

Example.

invoke showtable csv/poisson/MNIST/
PURE_dc_scale001_new                     optimal stopping : 384.30,     31.97/0.02      | ZCSC : 447.60,         31.26/0.02 | STE 31.99/0.02
PURE_dc_scale01_new                      optimal stopping : 94.70,      24.96/0.12      | ZCSC : 144.60,         24.04/0.14 | STE 24.89/0.12
PURE_dc_scale02_new                      optimal stopping : 70.30,      22.92/0.20      | ZCSC : 110.00,         21.82/0.22 | STE 22.83/0.20
<EXEPRIMENTAL NAME>                      optimal stopping :<STEP>,      <PSNR>/<LPIPS>  | ZCSC : <STEP>,      <PSNR>/<LPIPS>| STE <PSNR>/<LPIPS>

The reported numbers are PSNR/LPIPS.

Results in paper

For the result used on paper, please refer this link.

SSIM score

For SSIM score of color images, I used matlab code same as the author of S2S.
This is the demo code I received from the S2S author.
Thank you Mingqin!

% examples
ref = im2double(imread('gt.png'));
noisy = im2double(imread('noisy.png'));
psnr_result = psnr(ref, noisy);
ssim_result = ssim(ref, noisy);

License

MIT license.

Contacts

For questions, please send an email to [email protected]

Code and models for "Rethinking Deep Image Prior for Denoising" (ICCV 2021)

Related tags

Overview

DIP-denosing

Working environment

Set-up

Inference

Browsing experimental result

Results in paper

SSIM score

License

Contacts

Owner

Computer Vision Lab. @ GIST

This repo is developed for Strong Baseline For Vehicle Re-Identification in Track 2 Ai-City-2021 Challenges

This is the reference implementation for "Coresets via Bilevel Optimization for Continual Learning and Streaming"

piSTAR Lab is a modular platform built to make AI experimentation accessible and fun. (pistar.ai)

Code for LIGA-Stereo Detector, ICCV'21

Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking

PiRapGenerator - Make anyone rap the digits of pi

Code artifacts for the submission "Mind the Gap! A Study on the Transferability of Virtual vs Physical-world Testing of Autonomous Driving Systems"

Instantaneous Motion Generation for Robots and Machines.

Simple machine learning library / 簡單易用的機器學習套件

LTR_CrossEncoder: Legal Text Retrieval Zalo AI Challenge 2021

Official pytorch implementation of "DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion"

[TIP2020] Adaptive Graph Representation Learning for Video Person Re-identification

Generating retro pixel game characters with Generative Adversarial Networks. Dataset "TinyHero" included.

Multiple custom object count and detection using YOLOv3-Tiny method

Self-supervised Label Augmentation via Input Transformations (ICML 2020)

A Review of Deep Learning Techniques for Markerless Human Motion on Synthetic Datasets

[TPDS'21] COSCO: Container Orchestration using Co-Simulation and Gradient Based Optimization for Fog Computing Environments

Large-scale language modeling tutorials with PyTorch

Human head pose estimation using Keras over TensorFlow.

Ontologysim: a Owlready2 library for applied production simulation