High Dynamic Range Novel View Synthesis with Single Exposure

TL;DR

This paper introduces Mono-HDR-3D, a novel method for high dynamic range novel view synthesis using only single exposure images, overcoming limitations of multi-exposure approaches like motion artifacts and high costs.

Contribution

The paper presents the first single-exposure HDR-NVS framework with a novel unsupervised learning approach based on LDR image formation principles.

Findings

Mono-HDR-3D outperforms previous methods significantly.

The approach enables HDR-NVS with only single exposure images.

The method is adaptable and can be integrated with existing NVS models.

Abstract

High Dynamic Range Novel View Synthesis (HDR-NVS) aims to establish a 3D scene HDR model from Low Dynamic Range (LDR) imagery. Typically, multiple-exposure LDR images are employed to capture a wider range of brightness levels in a scene, as a single LDR image cannot represent both the brightest and darkest regions simultaneously. While effective, this multiple-exposure HDR-NVS approach has significant limitations, including susceptibility to motion artifacts (e.g., ghosting and blurring), high capture and storage costs. To overcome these challenges, we introduce, for the first time, the single-exposure HDR-NVS problem, where only single exposure LDR images are available during training. We further introduce a novel approach, Mono-HDR-3D, featuring two dedicated modules formulated by the LDR image formation principles, one for converting LDR colors to HDR counterparts, and the other for transforming HDR images to LDR format so that unsupervised learning is enabled in a closed loop. Designed as a meta-algorithm, our approach can be seamlessly integrated with existing NVS models. Extensive experiments show that Mono-HDR-3D significantly outperforms previous methods. Source code will be released.