HDRGS: High Dynamic Range Gaussian Splatting

TL;DR

HDR-GS introduces a novel high dynamic range Gaussian Splatting technique for efficient, accurate 3D HDR scene reconstruction from multi-exposure images, outperforming existing methods in speed and quality.

Contribution

The paper presents HDR-GS, a new method combining Gaussian Splatting with HDR-specific enhancements, improving reconstruction accuracy and efficiency over prior grid-based and implicit approaches.

Findings

Outperforms state-of-the-art in synthetic scenarios

Achieves faster convergence with coarse-to-fine strategy

Robust against sparse viewpoints and exposure extremes

Abstract

Recent years have witnessed substantial advancements in the field of 3D reconstruction from 2D images, particularly following the introduction of the neural radiance field (NeRF) technique. However, reconstructing a 3D high dynamic range (HDR) radiance field, which aligns more closely with real-world conditions, from 2D multi-exposure low dynamic range (LDR) images continues to pose significant challenges. Approaches to this issue fall into two categories: grid-based and implicit-based. Implicit methods, using multi-layer perceptrons (MLP), face inefficiencies, limited solvability, and overfitting risks. Conversely, grid-based methods require significant memory and struggle with image quality and long training times. In this paper, we introduce Gaussian Splatting-a recent, high-quality, real-time 3D reconstruction technique-into this domain. We further develop the High Dynamic Range Gaussian Splatting (HDR-GS) method, designed to address the aforementioned challenges. This method enhances color dimensionality by including luminance and uses an asymmetric grid for tone-mapping, swiftly and precisely converting pixel irradiance to color. Our approach improves HDR scene recovery accuracy and integrates a novel coarse-to-fine strategy to speed up model convergence, enhancing robustness against sparse viewpoints and exposure extremes, and preventing local optima. Extensive testing confirms that our method surpasses current state-of-the-art techniques in both synthetic and real-world scenarios.