iHDR: Iterative HDR Imaging with Arbitrary Number of Exposures

TL;DR

The paper introduces iHDR, a flexible iterative HDR imaging framework that fuses an arbitrary number of LDR images through a novel dual-input fusion network and a domain mapping network, outperforming existing methods.

Contribution

The paper presents a new iterative HDR fusion framework capable of handling any number of input images, unlike prior fixed-input methods.

Findings

Outperforms state-of-the-art HDR deghosting methods.

Effective with varying numbers of input frames.

Demonstrates superior qualitative and quantitative results.

Abstract

High dynamic range (HDR) imaging aims to obtain a high-quality HDR image by fusing information from multiple low dynamic range (LDR) images. Numerous learning-based HDR imaging methods have been proposed to achieve this for static and dynamic scenes. However, their architectures are mostly tailored for a fixed number (e.g., three) of inputs and, therefore, cannot apply directly to situations beyond the pre-defined limited scope. To address this issue, we propose a novel framework, iHDR, for iterative fusion, which comprises a ghost-free Dual-input HDR fusion network (DiHDR) and a physics-based domain mapping network (ToneNet). DiHDR leverages a pair of inputs to estimate an intermediate HDR image, while ToneNet maps it back to the nonlinear domain and serves as the reference input for the next pairwise fusion. This process is iteratively executed until all input frames are utilized. Qualitative and quantitative experiments demonstrate the effectiveness of the proposed method as compared to existing state-of-the-art HDR deghosting approaches given flexible numbers of input frames.