HDRGS: High Dynamic Range Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Jiahao, Xiao, Lu, Peng, Rui, Xiong, Kaiqiang, Wang, Ronggang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910681167560704
author Wu, Jiahao
Xiao, Lu
Peng, Rui
Xiong, Kaiqiang
Wang, Ronggang
author_facet Wu, Jiahao
Xiao, Lu
Peng, Rui
Xiong, Kaiqiang
Wang, Ronggang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06543
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HDRGS: High Dynamic Range Gaussian Splatting
Wu, Jiahao
Xiao, Lu
Peng, Rui
Xiong, Kaiqiang
Wang, Ronggang
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title HDRGS: High Dynamic Range Gaussian Splatting
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2408.06543