Intrinsic Image Harmonization

Last update: Dec 21, 2022

Related tags

Deep Learning IntrinsicHarmony

Overview

Intrinsic Image Harmonization [Paper]

Zonghui Guo, Haiyong Zheng, Yufeng Jiang, Zhaorui Gu, Bing Zheng

Here we provide PyTorch implementation and the trained model of our framework.

Prerequisites

Linux
Python 3
CPU or NVIDIA GPU + CUDA CuDNN

Train/Test

Download iHarmony4 dataset, and our HVIDIT dataset Google Drive or BaiduCloud (access code: akbi).
Train a model:

CUDA_VISIBLE_DEVICES=0 python train.py --model retinexltifpm  --name retinexltifpm_allihd  --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx

Test the model

CUDA_VISIBLE_DEVICES=0 python test.py --model retinexltifpm  --name retinexltifpm_allihd  --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx

Apply a pre-trained model

Download the pretrained model from Google Drive or BaiduCloud (access code: 20m6), and put net_G.pth in the directory checkpoints/experiment. Run:

CUDA_VISIBLE_DEVICES=0 python test.py --model retinexltifpm  --name experiment  --dataset_root <dataset_dir> --dataset_name IHD --batch_size xx --init_port xxxx

Evaluation

We provide the code in ih_evaluation.py. Run:

CUDA_VISIBLE_DEVICES=0 python evaluation/ih_evaluation.py --dataroot <dataset_dir> --result_root  results/experiment/test_latest/images/ --evaluation_type our --dataset_name ALL

Quantitative Result

Dataset	Metrics	Composite	Ours (iHarmony4)	Ours (iHarmony4+HVIDIT)
HCOCO	PSNR MSE fMSE	33.99 69.37 996.59	37.61 23.25 386.39	37.77 21.84 367.38
HAdobe5k	PSNR MSE fMSE	28.52 345.54 2051.61	36.20 42.21 296.76	36.49 39.53 266.49
HFlickr	PSNR MSE fMSE	28.43 264.35 1574.37	31.74 100.86 676.71	32.08 96.87 635.60
Hday2night	PSNR MSE fMSE	34.36 109.65 1409.98	36.48 50.64 755.88	36.60 50.37 763.33
HVIDIT	PSNR MSE fMSE	38.72 53.12 1604.41	- - -	41.83 22.49 691.06
ALL	PSNR MSE fMSE	32.07 167.39 1386.12	36.53 37.95 399.34	36.96 35.33 388.50

Bibtex

If you use this code for your research, please cite our papers.

@InProceedings{Guo_2021_CVPR,
    author    = {Guo, Zonghui and Zheng, Haiyong and Jiang, Yufeng and Gu, Zhaorui and Zheng, Bing},
    title     = {Intrinsic Image Harmonization},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {16367-16376}
}

Acknowledgement

For some of the data modules and model functions used in this source code, we need to acknowledge the repo of DoveNet and CycleGAN.

You might also like...

python library for invisible image watermark (blind image watermark)

invisible-watermark invisible-watermark is a python library and command line tool for creating invisible watermark over image.(aka. blink image waterm

572 Jan 7, 2023

AOT-GAN for High-Resolution Image Inpainting (codebase for image inpainting)

AOT-GAN for High-Resolution Image Inpainting Arxiv Paper | AOT-GAN: Aggregated Contextual Transformations for High-Resolution Image Inpainting Yanhong

214 Jan 3, 2023

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

arXiv Dual Contrastive Learning Adversarial Generative Networks (DCLGAN) We provide our PyTorch implementation of DCLGAN, which is a simple yet powerf

119 Dec 4, 2022

Deep Image Search is an AI-based image search engine that includes deep transfor learning features Extraction and tree-based vectorized search.

Deep Image Search - AI-Based Image Search Engine Deep Image Search is an AI-based image search engine that includes deep transfer learning features Ex

139 Jan 1, 2023

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

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

61 Jan 1, 2023

[CVPR 2021] Teachers Do More Than Teach: Compressing Image-to-Image Models (CAT)

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set —— PyTorch implementation This is an unofficial offici

833 Dec 28, 2022

Comments

Model Inference

Hello, is there a way to infer the model by reading an image and passing the image and its mask to the model and getting the harmonized output? Without the need to store the image's path in a text file and reading it from the text file then loading the image?

opened by AhmedHashish123 2
visdom interface is blank

first，thanks for your excellent work！ When I execute the training code, the visdom interface does not display the result picture and the training loss. it works when I execute the code of dovenet. could you tell me how to solve this problem? thanks again

opened by Ligouhi 0

Releases(v1.0)

v1.0(Feb 9, 2022)

Code version of our CVPR work [Paper].
Source code(tar.gz)
Source code(zip)

Intrinsic Image Harmonization

Related tags

Overview

Intrinsic Image Harmonization [Paper]

Prerequisites

Train/Test

Apply a pre-trained model

Evaluation

Quantitative Result

Bibtex

Acknowledgement

You might also like...

python library for invisible image watermark (blind image watermark)

AOT-GAN for High-Resolution Image Inpainting (codebase for image inpainting)

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

Deep Image Search is an AI-based image search engine that includes deep transfor learning features Extraction and tree-based vectorized search.

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

[CVPR 2021] Teachers Do More Than Teach: Compressing Image-to-Image Models (CAT)

Official implementation of "SinIR: Efficient General Image Manipulation with Single Image Reconstruction" (ICML 2021)

This is the PyTorch implementation of GANs N’ Roses: Stable, Controllable, Diverse Image to Image Translation

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.

Comments

Model Inference

visdom interface is blank

Releases(v1.0)

v1.0(Feb 9, 2022)

Owner

VISION @ OUC

Label Hallucination for Few-Shot Classification

Python implementation of MULTIseq barcode alignment using fuzzy string matching and GMM barcode assignment

Grow Function: Generate 3D Stacked Bifurcating Double Deep Cellular Automata based organisms which differentiate using a Genetic Algorithm...

We propose a new method for effective shadow removal by regarding it as an exposure fusion problem.

PyTorch implementations of the beta divergence loss.

PyTorch code of paper "LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering"

Implementing yolov4 target detection and tracking based on nao robot

This program writes christmas wish programmatically. It is using turtle as a pen pointer draw christmas trees and stars.

SatelliteSfM - A library for solving the satellite structure from motion problem

Extracting knowledge graphs from language models as a diagnostic benchmark of model performance.

[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis

Codebase for testing whether hidden states of neural networks encode discrete structures.

SCALoss: Side and Corner Aligned Loss for Bounding Box Regression (AAAI2022).

Pyeventbus: a publish/subscribe event bus

[CVPR 2022] Official code for the paper: "A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration"

OOD Generalization and Detection (ACL 2020)

Video2x - A lossless video/GIF/image upscaler achieved with waifu2x, Anime4K, SRMD and RealSR.

Semantic Scholar's Author Disambiguation Algorithm & Evaluation Suite

BridgeGAN - Tensorflow implementation of Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translation.

Trajectory Variational Autoencder baseline for Multi-Agent Behavior challenge 2022