Lightweight Improved Residual Network for Efficient Inverse Tone Mapping

TL;DR

This paper introduces a lightweight residual network that efficiently converts SDR images to HDR, achieving state-of-the-art results with reduced computational complexity.

Contribution

It proposes a novel Improved Residual Block (IRB) and a lightweight IRNet architecture for efficient inverse tone mapping of SDR to HDR images.

Findings

IRNet achieves state-of-the-art performance on benchmark datasets.

The proposed IRB effectively fuses multi-layer features for HDR reconstruction.

The model is computationally efficient and suitable for real-world applications.

Abstract

The display devices like HDR10 televisions are increasingly prevalent in our daily life for visualizing high dynamic range (HDR) images. But the majority of media images on the internet remain in 8-bit standard dynamic range (SDR) format. Therefore, converting SDR images to HDR ones by inverse tone mapping (ITM) is crucial to unlock the full potential of abundant media images. However, existing ITM methods are usually developed with complex network architectures requiring huge computational costs. In this paper, we propose a lightweight Improved Residual Network (IRNet) by enhancing the power of popular residual block for efficient ITM. Specifically, we propose a new Improved Residual Block (IRB) to extract and fuse multi-layer features for fine-grained HDR image reconstruction. Experiments on three benchmark datasets demonstrate that our IRNet achieves state-of-the-art performance on both the ITM and joint SR-ITM tasks. The code, models and data will be publicly available at https://github.com/ThisisVikki/ITM-baseline.