Skip to content

[CVPR 2020] Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

Notifications You must be signed in to change notification settings

alex04072000/SingleHDR

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ce89648 · Dec 11, 2021

History

41 Commits
Mar 8, 2020
Aug 26, 2021
Aug 28, 2021
Apr 25, 2020
Apr 25, 2020
Mar 28, 2020
Dec 11, 2021
Mar 8, 2020
Mar 8, 2020
Dec 11, 2021
Mar 8, 2020
Mar 8, 2020
Mar 8, 2020
Mar 8, 2020
Apr 1, 2020
Mar 8, 2020
Mar 8, 2020
Mar 28, 2020
Mar 8, 2020

Repository files navigation

Important update (2020/09/13)

Training code uploaded. Please refer to training_code folder and follow the instructions in the readme file.

Important update (2020/07/10)

The webpage and the links to the dataset will not be accessible. The temporary links to the peoject website and dataset are below:

Project website

Training data

Testing data (HDR-Synth)

Testing data (HDR-Real)

Testing data (RAISE)

Testing data (HDR-Eye)

Pre-trained weights

Sorry for the inconvenience.

[CVPR 2020] Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

Recovering a high dynamic range (HDR) image from asingle low dynamic range (LDR) input image is challenging due to missing details in under-/over-exposed regions caused by quantization and saturation of camera sensors. In contrast to existing learning-based methods, our core idea is to incorporate the domain knowledge of the LDR image formation pipeline into our model. We model the HDR-to-LDR image formation pipeline as the (1) dynamic range clipping, (2) non-linear mapping from a camera response function, and (3) quantization. We then propose to learn three specialized CNNs to reverse these steps. By decomposing the problem into specific sub-tasks, we impose effective physical constraints to facilitate the training of individual sub-networks. Finally, we jointly fine-tune the entire model end-to-end to reduce error accumulation. With extensive quantitative and qualitative experiments on diverse image datasets, we demonstrate that the proposed method performs favorably against state-of-the-art single-image HDR reconstruction algorithms. The source code, datasets, and pre-trained model are available at our project website.

[Project]

Paper

Paper

Overview

This is the author's reference implementation of the single-image HDR reconstruction using TensorFlow described in: "Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline" Yu-Lun Liu, Wei-Sheng Lai, Yu-Sheng Chen, Yi-Lung Kao, Ming-Hsuan Yang, Yung-Yu Chuang, Jia-Bin Huang (National Taiwan University & Google & Virginia Tech & University of California at Merced & MediaTek Inc.) in CVPR 2020. If you find this code useful for your research, please consider citing the following paper.

Further information please contact Yu-Lun Liu.

Requirements setup

  • TensorFlow

    • tested using TensorFlow 1.10.0
  • To download the pre-trained models:

Usage

  • Run your own images (using the model trained on our synthetic training data):
CUDA_VISIBLEDEVICES=0 python3 test_real.py --ckpt_path_deq ckpt_deq/model.ckpt --ckpt_path_lin ckpt_lin/model.ckpt --ckpt_path_hal ckpt_hal/model.ckpt --test_imgs ./imgs --output_path output_hdrs
  • Run your own images (using the model fine-tuned on both synthetic and real training data):
CUDA_VISIBLEDEVICES=0 python3 test_real_refinement.py --ckpt_path ckpt_deq_lin_hal_ref/model.ckpt --test_imgs ./imgs --output_path output_hdrs

Citation

[1] Yu-Lun Liu, Wei-Sheng Lai, Yu-Sheng Chen, Yi-Lung Kao, Ming-Hsuan Yang, Yung-Yu Chuang, and Jia-Bin Huang. Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[2] Gabriel Eilertsen, Joel Kronander, Gyorgy Denes, Rafa\l Mantiuk, and Jonas Unger. HDR image reconstruction from a single exposure using deep CNNs. ACM Transactions on Graphics (TOG), 2017

Acknowledgment

Parts of the code in hallucination_net.py are folked from HDRCNN.

About

[CVPR 2020] Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published