Casual3DHDR: Deblurring High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gong, Shucheng, Zhao, Lingzhe, Li, Wenpu, Xie, Hong, Zhang, Yin, Zhao, Shiyu, Liu, Peidong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916903939735552
author Gong, Shucheng
Zhao, Lingzhe
Li, Wenpu
Xie, Hong
Zhang, Yin
Zhao, Shiyu
Liu, Peidong
author_facet Gong, Shucheng
Zhao, Lingzhe
Li, Wenpu
Xie, Hong
Zhang, Yin
Zhao, Shiyu
Liu, Peidong
contents Photo-realistic novel view synthesis from multi-view images, such as neural radiance field (NeRF) and 3D Gaussian Splatting (3DGS), has gained significant attention for its superior performance. However, most existing methods rely on low dynamic range (LDR) images, limiting their ability to capture detailed scenes in high-contrast environments. While some prior works address high dynamic range (HDR) scene reconstruction, they typically require multi-view sharp images with varying exposure times captured at fixed camera positions, which is time-consuming and impractical. To make data acquisition more flexible, we propose \textbf{Casual3DHDR}, a robust one-stage method that reconstructs 3D HDR scenes from casually-captured auto-exposure (AE) videos, even under severe motion blur and unknown, varying exposure times. Our approach integrates a continuous-time camera trajectory into a unified physical imaging model, jointly optimizing exposure times, camera trajectory, and the camera response function (CRF). Extensive experiments on synthetic and real-world datasets demonstrate that \textbf{Casual3DHDR} outperforms existing methods in robustness and rendering quality. Our source code and dataset will be available at https://lingzhezhao.github.io/CasualHDRSplat/
format Preprint
id arxiv_https___arxiv_org_abs_2504_17728
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Casual3DHDR: Deblurring High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos
Gong, Shucheng
Zhao, Lingzhe
Li, Wenpu
Xie, Hong
Zhang, Yin
Zhao, Shiyu
Liu, Peidong
Computer Vision and Pattern Recognition
Graphics
Multimedia
Photo-realistic novel view synthesis from multi-view images, such as neural radiance field (NeRF) and 3D Gaussian Splatting (3DGS), has gained significant attention for its superior performance. However, most existing methods rely on low dynamic range (LDR) images, limiting their ability to capture detailed scenes in high-contrast environments. While some prior works address high dynamic range (HDR) scene reconstruction, they typically require multi-view sharp images with varying exposure times captured at fixed camera positions, which is time-consuming and impractical. To make data acquisition more flexible, we propose \textbf{Casual3DHDR}, a robust one-stage method that reconstructs 3D HDR scenes from casually-captured auto-exposure (AE) videos, even under severe motion blur and unknown, varying exposure times. Our approach integrates a continuous-time camera trajectory into a unified physical imaging model, jointly optimizing exposure times, camera trajectory, and the camera response function (CRF). Extensive experiments on synthetic and real-world datasets demonstrate that \textbf{Casual3DHDR} outperforms existing methods in robustness and rendering quality. Our source code and dataset will be available at https://lingzhezhao.github.io/CasualHDRSplat/
title Casual3DHDR: Deblurring High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos
topic Computer Vision and Pattern Recognition
Graphics
Multimedia
url https://arxiv.org/abs/2504.17728