A Two-stage Deep Network for High Dynamic Range Image Reconstruction (2021-04-19T00:00:00.000000Z)

TL;DR

The qualitative and quantitative comparisons demonstrate that the proposed method can outperform the existing LDR to HDR works with a marginal difference and can reconstruct plausible HDR images without presenting any visual artefacts.

Abstract

Mapping a single exposure low dynamic range (LDR) image into a high dynamic range (HDR) is considered among the most strenuous image to image translation tasks due to exposure-related missing information. This study tackles the challenges of single-shot LDR to HDR mapping by proposing a novel two-stage deep network. Notably, our proposed method aims to reconstruct an HDR image with-out knowing hardware information, including camera response function (CRF) and exposure settings. Therefore, we aim to perform image enhancement task like denoising, exposure correction, etc., in the first stage. Additionally, the second stage of our deep network learns tone mapping and bit-expansion from a convex set of data samples. The qualitative and quantitative comparisons demonstrate that the proposed method can outperform the existing LDR to HDR works with a marginal difference. Apart from that, we collected an LDR image dataset incorporating different camera systems. The evaluation with our collected real-world LDR images illustrates that the proposed method can reconstruct plausible HDR images without presenting any visual artefacts. Code available : https://github.com/sharif-apu/twostageHDR_NTIRE21.

Authors

R. A. Naqvi

5 papers

Mithun Biswas

5 papers

S. Sharif

4 papers

TL;DR

Abstract

Authors

References43 items

Generative Adversarial Networks

NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results

Beyond Joint Demosaicking and Denoising: An Image Processing Pipeline for a Pixel-bin Image Sensor

Learning Medical Image Denoising with Deep Dynamic Residual Attention Network

Importance-weighted conditional adversarial network for unsupervised domain adaptation

Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline

Replacing Mobile Camera ISP with a Single Deep Learning Model

Deep Learning on Image Denoising: An overview

FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network

Deep Recursive HDRI: Inverse Tone Mapping Using Generative Adversarial Networks

ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

CBAM: Convolutional Block Attention Module

ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content

Residual Dense Network for Image Super-Resolution

DeepISP: Toward Learning an End-to-End Image Processing Pipeline

Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Image

Deep reverse tone mapping

HDR image reconstruction from a single exposure using deep CNNs

Advanced High Dynamic Range Imaging

DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks

Loss Functions for Image Restoration With Neural Networks

Tone expansion using lighting style aesthetics

Dynamic range expansion based on image statistics

U-Net: Convolutional Networks for Biomedical Image Segmentation

Adam: A Method for Stochastic Optimization

Conditional Generative Adversarial Nets

Very Deep Convolutional Networks for Large-Scale Image Recognition

Automatic Exposure Correction of Consumer Photographs

Color correction for tone mapping

Enhancement of Bright Video Features for HDR Displays

Ldr2Hdr: on-the-fly reverse tone mapping of legacy video and photographs

High dynamic range image hallucination

Inverse tone mapping

Evaluation of tone mapping operators using a High Dynamic Range display

The development of the CIE 2000 Colour Difference Formula

Recovering high dynamic range radiance maps from photographs

Over-Exposure Correction via Exposure and Scene Information Disentanglement

NTIRE HDR Challange code

PyTorch Framework code

A median cut algorithm for light probe sampling

A Review of Image Denoising Algorithms, with a New One

Production-Ready Global Illumination

Lorne

Field of Study

Journal Information

Name

Page