Pytorch implementation of various High Dynamic Range (HDR) Imaging algorithms

Last update: Nov 16, 2022

Related tags

Overview

Deep High Dynamic Range Imaging Benchmark

This repository is the pytorch implementation of various High Dynamic Range (HDR) Imaging algorithms. Please find the details below.

Maintenance and Contributors

@TianhongDai and @WeiLi-THU

Requirements

pytorch==1.4.0
opencv-python
scikit-image==0.17.2

ToDo List

adaptive padding
add more baselines

Supported Algorthms

DeepHDR [1]
NHDRRNet [2]
AHDR [3]
DAHDR [4]

Instruction

download the Kalantari dataset via: [link], and organize the dataset as follows:

dataset
│
└───Traning
│   │  001
│   │  002
│   │  003
│   |  ...
│   
└───Test
    │  001
    │  002
    |  003
    |  ...

train the network [unet|nhdrrnet|ahdr|dahdr]:

python train.py --net-type unet --cuda --batch-size 8 --lr 0.0002

continue training using the pre-saved checkpoint:

python train.py --net-type unet --cuda --resume --last-ckpt-path <the saved ckpt path>

test the model and save HDR images:

python eval_metric.py --net-type unet --model-path <the saved ckpt path> --cuda --save-image

Pre-trained Models

The pre-trained models can be downloaded from the released page.

Performance

	DeepHDR[1]	NHDRRNet[2]	AHDR[3]	DAHDR[4]
PSNR-$\mu$	42.2695	42.4769	43.5742	43.5240
SSIM-$\mu$	0.9941	0.9942	0.9956	0.9956
PSNR-L	40.0627	40.1978	41.1551	40.7534
SSIM-L	0.9892	0.9889	0.9903	0.9905

Acknowledgements

@elliottwu for DeepHDR
@qingsenyangit for AHDRNet
@Galaxies99 for NHDRRNet details

References

[1] Deep High Dynamic Range Imaging with Large Foreground Motions
[2] Deep HDR Imaging via A Non-Local Network
[3] Attention-guided Network for Ghost-free High Dynamic Range Imaging
[4] Dual-Attention-Guided Network for Ghost-Free High Dynamic Range Imaging

You might also like...

Dynamic vae - Dynamic VAE algorithm is used for anomaly detection of battery data

Dynamic VAE frame Automatic feature extraction can be achieved by probability di

10 Oct 7, 2022

The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

Face Alignment in Full Pose Range: A 3D Total Solution By Jianzhu Guo. [Updates] 2020.8.30: The pre-trained model and code of ECCV-20 are made public

3.4k Jan 2, 2023

Implementation for our ICCV2021 paper: Internal Video Inpainting by Implicit Long-range Propagation

Implicit Internal Video Inpainting Implementation for our ICCV2021 paper: Internal Video Inpainting by Implicit Long-range Propagation paper | project

202 Dec 30, 2022

A medical imaging framework for Pytorch

Welcome to MedicalTorch MedicalTorch is an open-source framework for PyTorch, implementing an extensive set of loaders, pre-processors and datasets fo

799 Jan 3, 2023

Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging, ICCV2021 [PyTorch Code]

20 Oct 24, 2022

Official implementation of NLOS-OT: Passive Non-Line-of-Sight Imaging Using Optimal Transport (IEEE TIP, accepted)

NLOS-OT Official implementation of NLOS-OT: Passive Non-Line-of-Sight Imaging Using Optimal Transport (IEEE TIP, accepted) Description In this reposit

16 Dec 16, 2022

Official Keras Implementation for UNet++ in IEEE Transactions on Medical Imaging and DLMIA 2018

UNet++: A Nested U-Net Architecture for Medical Image Segmentation UNet++ is a new general purpose image segmentation architecture for more accurate i

1.8k Jan 7, 2023

Official implementation of the method ContIG, for self-supervised learning from medical imaging with genomics

ContIG: Self-supervised Multimodal Contrastive Learning for Medical Imaging with Genetics This is the code implementation of the paper "ContIG: Self-s

22 Dec 13, 2022

This is the official implementation code repository of Underwater Light Field Retention : Neural Rendering for Underwater Imaging (Accepted by CVPR Workshop2022 NTIRE)

Underwater Light Field Retention : Neural Rendering for Underwater Imaging (UWNR) (Accepted by CVPR Workshop2022 NTIRE) Authors: Tian Ye†, Sixiang Che

17 Dec 14, 2022

Pytorch implementation of various High Dynamic Range (HDR) Imaging algorithms

Related tags

Overview

Deep High Dynamic Range Imaging Benchmark

Maintenance and Contributors

Requirements

ToDo List

Supported Algorthms

Instruction

Pre-trained Models

Performance

Acknowledgements

References

You might also like...

Dynamic vae - Dynamic VAE algorithm is used for anomaly detection of battery data

The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

Implementation for our ICCV2021 paper: Internal Video Inpainting by Implicit Long-range Propagation

A medical imaging framework for Pytorch

Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging, ICCV2021 [PyTorch Code]

Official implementation of NLOS-OT: Passive Non-Line-of-Sight Imaging Using Optimal Transport (IEEE TIP, accepted)

Official Keras Implementation for UNet++ in IEEE Transactions on Medical Imaging and DLMIA 2018

Official implementation of the method ContIG, for self-supervised learning from medical imaging with genomics

This is the official implementation code repository of Underwater Light Field Retention : Neural Rendering for Underwater Imaging (Accepted by CVPR Workshop2022 NTIRE)

Releases(v1.0.0)

v1.0.0(Feb 3, 2022)

Owner

Tianhong Dai

Adversarial Reweighting for Partial Domain Adaptation

In-Place Activated BatchNorm for Memory-Optimized Training of DNNs

This project deploys a yolo fastest model in the form of tflite on raspberry 3b+. The model is from another repository of mine called -Trash-Classification-Car

Aesara is a Python library that allows one to define, optimize, and efficiently evaluate mathematical expressions involving multi-dimensional arrays.

SCAN: Learning to Classify Images without Labels, incl. SimCLR. [ECCV 2020]

A template repository for submitting a job to the Slurm Cluster installed at the DISI - University of Bologna

Simple, efficient and flexible vision toolbox for mxnet framework.

Learning to Identify Top Elo Ratings with A Dueling Bandits Approach

Deep Learning segmentation suite designed for 2D microscopy image segmentation

A Self-Supervised Contrastive Learning Framework for Aspect Detection

DrQ-v2: Improved Data-Augmented Reinforcement Learning

CS5242_2021 - Neural Networks and Deep Learning, NUS CS5242, 2021

Matching python environment code for Lux AI 2021 Kaggle competition, and a gym interface for RL models.

Align and Prompt: Video-and-Language Pre-training with Entity Prompts

Analysis of Antarctica sequencing samples contaminated with SARS-CoV-2

Apache Spark - A unified analytics engine for large-scale data processing

Byte-based multilingual transformer TTS for low-resource/few-shot language adaptation.

[Preprint] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

Using LSTM write Tang poetry

An index of recommendation algorithms that are based on Graph Neural Networks.