A Two-stage Deep Network for High Dynamic Range Image Reconstruction

TL;DR

This paper introduces a novel two-stage deep learning approach for converting single low dynamic range images into high dynamic range images without requiring camera-specific information, outperforming existing methods.

Contribution

The proposed method uniquely reconstructs HDR images from LDR inputs without needing camera response or exposure data, using a two-stage network for enhancement and tone mapping.

Findings

Outperforms existing LDR to HDR methods with marginal difference

Can reconstruct plausible HDR images without visual artifacts

Effective on real-world LDR images from various camera systems

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 without 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.