GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → sjmoran → CURL

sjmoran / CURL

Licence: other
Code for the ICPR 2020 paper: "CURL: Neural Curve Layers for Image Enhancement"

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Labels

imagecomputer-visionphotoshoppaperimage-processingcomputational-photographycvprimage-enhancementeccvraw2rgbaccvrgb-imagesicpr2020neural-curve-layersadobe-upe-datasetrgb-pairs

Projects that are alternatives of or similar to CURL

Awesome-Computer-Vision-Paper-List
This repository contains all the papers accepted in top conference of computer vision, with convenience to search related papers.
Stars: ✭ 248 (+40.11%)
Mutual labels:  paper, cvpr, eccv
Pwc
Papers with code. Sorted by stars. Updated weekly.
Stars: ✭ 15,288 (+8537.29%)
Mutual labels:  paper, cvpr, eccv
cool-papers-in-pytorch
Reimplementing cool papers in PyTorch...
Stars: ✭ 21 (-88.14%)
Mutual labels:  paper, cvpr
TMNet
The official pytorch implemention of the CVPR paper "Temporal Modulation Network for Controllable Space-Time Video Super-Resolution".
Stars: ✭ 77 (-56.5%)
Mutual labels:  paper, cvpr
GuidedLabelling
Exploiting Saliency for Object Segmentation from Image Level Labels, CVPR'17
Stars: ✭ 35 (-80.23%)
Mutual labels:  paper, cvpr
Guided-I2I-Translation-Papers
Guided Image-to-Image Translation Papers
Stars: ✭ 117 (-33.9%)
Mutual labels:  cvpr, eccv
Restoring-Extremely-Dark-Images-In-Real-Time
The project is the official implementation of our CVPR 2021 paper, "Restoring Extremely Dark Images in Real Time"
Stars: ✭ 79 (-55.37%)
Mutual labels:  paper, cvpr
NeuroAI
NeuroAI-UW seminar, a regular weekly seminar for the UW community, organized by NeuroAI Shlizerman Lab.
Stars: ✭ 36 (-79.66%)
Mutual labels:  cvpr, eccv
Cvpr 2019 Paper Statistics
Statistics and Visualization of acceptance rate, main keyword of CVPR 2019 accepted papers for the main Computer Vision conference (CVPR)
Stars: ✭ 527 (+197.74%)
Mutual labels:  paper, cvpr
Cv paperdaily
CV 论文笔记
Stars: ✭ 555 (+213.56%)
Mutual labels:  paper, cvpr
Papercrawler
Crawler used to crawl papers
Stars: ✭ 20 (-88.7%)
Mutual labels:  paper, cvpr
Cvpr2021 Papers With Code
CVPR 2021 论文和开源项目合集
Stars: ✭ 7,138 (+3932.77%)
Mutual labels:  paper, cvpr
Deeplpf
Code for CVPR 2020 paper "Deep Local Parametric Filters for Image Enhancement"
Stars: ✭ 91 (-48.59%)
Mutual labels:  paper, cvpr
AIPaperCompleteDownload
Complete download for papers in various top conferences
Stars: ✭ 64 (-63.84%)
Mutual labels:  paper, cvpr
AdvPC
AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds (ECCV 2020)
Stars: ✭ 35 (-80.23%)
Mutual labels:  paper
DynamicEntitySummarization-DynES
Dynamic Entity Summarization (DynES)
Stars: ✭ 21 (-88.14%)
Mutual labels:  paper
texturize
🤖🖌️ Generate photo-realistic textures based on source images. Remix, remake, mashup! Useful if you want to create variations on a theme or elaborate on an existing texture.
Stars: ✭ 495 (+179.66%)
Mutual labels:  computational-photography
ode-lstms
Code repository of the paper Learning Long-Term Dependencies in Irregularly-Sampled Time Series
Stars: ✭ 72 (-59.32%)
Mutual labels:  paper
awesome-secure-computation
Awesome list for cryptographic secure computation paper. This repo includes *Lattice*, *DifferentialPrivacy*, *MPC* and also a comprehensive summary for top conferences.
Stars: ✭ 125 (-29.38%)
Mutual labels:  paper
jpeg-defense
SHIELD: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression
Stars: ✭ 82 (-53.67%)
Mutual labels:  paper
View All Similar Projects ➔

CURL: Neural Curve Layers for Global Image Enhancement (ICPR 2020)

Sean Moran, Steven McDonagh, Greg Slabaugh

Huawei Noah's Ark Lab

Repository links for the paper CURL: Neural Curve Layers for Global Image Enhancement. In this repository you will find a link to the code and information of the datasets. Please raise a Github issue if you need assistance of have any questions on the research.

BATCH SIZE: Note this code is designed for a batch size of 1. It needs re-engineered to support higher batch sizes. Using higher batch sizes is not supported currently. To replicate our reported results please use a batch size of 1 only. If you do have a patch for CURL to support higher batch sizes please raise a pull request on this repo and we will integrate.

UPDATE 30th May 2022: Github user mahdip72 has kindly provided a refactored version of CURL. See Issue 31. A copy can also be found in CURL_refactored.gz. Note the authors of the paper have not tested this version of CURL.

UPDATE 19th April 2022: Github user barbodpj has kindly provided a batch > 1 version of CURL. See Issue 27. A copy can also be found in CURL_large_batch.tar.gz. Note the authors of the paper have not tested this version of CURL.

[Paper] [Supplementary] [Video] [Poster] [Slides]

Input Label Ours (CURL)
Input Label Ours (CURL)
Input Label Ours (CURL)

Requirements

requirements.txt contains the Python packages used by the code.

How to train CURL and use the model for inference

Training CURL

Instructions:

To get this code working on your system / problem you will need to edit the data loading functions, as follows:

  1. main.py, change the paths for the data directories to point to your data directory
  2. data.py, lines 248, 256, change the folder names of the data input and output directories to point to your folder names

To train, run the command:

python3 main.py

Inference - Using Pre-trained Models for Prediction

The directory pretrained_models contains a CURL pre-trained model on the Adobe5K_DPE dataset. The model with the highest validation dataset PSNR (23.58dB) is at epoch 510:

  • curl_validpsnr_23.073045286204017_validloss_0.0701291635632515_testpsnr_23.584083321292365_testloss_0.061363041400909424_epoch_510_model.pt

This pre-trained CURL model obtains 23.58dB on the test dataset for Adobe DPE.

To use this model for inference:

  1. Place the images you wish to infer in a directory e.g. ./adobe5k_dpe/curl_example_test_input/. Make sure the directory path has the word "input" somewhere in the path.
  2. Place the images you wish to use as groundtruth in a directory e.g. ./adobe5k_dpe/curl_example_test_output/. Make sure the directory path has the word "output" somewhere in the path.
  3. Place the names of the images (without extension) in a text file in the directory above the directory containing the images i.e. ./adobe5k_dpe/ e.g. ./adobe5k_dpe/images_inference.txt
  4. Run the command and the results will appear in a timestamped directory in the same directory as main.py:
python3 main.py --inference_img_dirpath=./adobe5k_dpe/ --checkpoint_filepath=./pretrained_models/curl_validpsnr_23.073045286204017_validloss_0.0701291635632515_testpsnr_23.584083321292365_testloss_0.061363041400909424_epoch_510_model.pt

CURL for RGB images

  • rgb_ted.py contains the TED model for RGB images

CURL for RAW images

  • raw_ted.py contains the TED model for RGB images

Github user contributions

CURL_for_RGB_images.zip is a contribution (RGB model and pre-trained weights) courtsey of Github user hermosayhl

Bibtex

If you do use ideas from the paper in your research please kindly consider citing as below:

@INPROCEEDINGS{moran2020curl,
  author={Moran, Sean and McDonagh, Steven and Slabaugh, Gregory},
  booktitle={2020 25th International Conference on Pattern Recognition (ICPR)}, 
  title={CURL: Neural Curve Layers for Global Image Enhancement}, 
  year={2021},
  volume={},
  number={},
  pages={9796-9803},
  doi={10.1109/ICPR48806.2021.9412677}}

Datasets

  • Samsung S7 (110 images, RAW, RGB pairs): this dataset can be downloaded here. The validation and testing images are listed below, the remaining images serve as our training dataset. For all results in the paper we use random crops of patch size 512x512 pixels during training.

    • Validation Dataset Images

      • S7-ISP-Dataset-20161110_125321
      • S7-ISP-Dataset-20161109_131627
      • S7-ISP-Dataset-20161109_225318
      • S7-ISP-Dataset-20161110_124727
      • S7-ISP-Dataset-20161109_130903
      • S7-ISP-Dataset-20161109_222408
      • S7-ISP-Dataset-20161107_234316
      • S7-ISP-Dataset-20161109_132214
      • S7-ISP-Dataset-20161109_161410
      • S7-ISP-Dataset-20161109_140043

    • Test Dataset Images

      • S7-ISP-Dataset-20161110_130812
      • S7-ISP-Dataset-20161110_120803
      • S7-ISP-Dataset-20161109_224347
      • S7-ISP-Dataset-20161109_155348
      • S7-ISP-Dataset-20161110_122918
      • S7-ISP-Dataset-20161109_183259
      • S7-ISP-Dataset-20161109_184304
      • S7-ISP-Dataset-20161109_131033
      • S7-ISP-Dataset-20161110_130117
      • S7-ISP-Dataset-20161109_134017

  • Adobe-DPE (5000 images, RGB, RGB pairs): this dataset can be downloaded here. After downloading this dataset you will need to use Lightroom to pre-process the images according to the procedure outlined in the DeepPhotoEnhancer (DPE) paper. Please see the issue here for instructions. Artist C retouching is used as the groundtruth/target. Note, that the images should be extracted in sRGB space. Feel free to raise a Gitlab issue if you need assistance with this (or indeed the Adobe-UPE dataset below). You can also find the training, validation and testing dataset splits for Adobe-DPE in the following file.

  • Adobe-UPE (5000 images, RGB, RGB pairs): this dataset can be downloaded here. As above, you will need to use Lightroom to pre-process the images according to the procedure outlined in the Underexposed Photo Enhancement Using Deep Illumination Estimation (DeepUPE) paper and detailed in the issue here. Artist C retouching is used as the groundtruth/target. You can find the test images for the Adobe-UPE dataset at this link.

License

BSD-3-Clause License

Contributions

We appreciate all contributions. If you are planning to contribute back bug-fixes, please do so without any further discussion.

If you plan to contribute new features, utility functions or extensions to the core, please first open an issue and discuss the feature with us. Sending a PR without discussion might end up resulting in a rejected PR, because we might be taking the core in a different direction than you might be aware of.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].