Gaussian in the Dark: Real‐Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting
Computer Graphics Forum · 2024-10 · 43 (7)
DOI: 10.1111/cgf.15213 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 24.10.2024. Verfasst von Sheng Ye und 4 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: Beijing Science and Technology Planning Project.
Abstract (Originalsprache)
3D Gaussian Splatting has recently emerged as a powerful representation that can synthesize remarkable novel views using consistent multi‐view images as input. However, we notice that images captured in dark environments where the scenes are not fully illuminated can exhibit considerable brightness variations and multi‐view inconsistency, which poses great challenges to 3D Gaussian Splatting and severely degrades its performance. To tackle this problem, we propose Gaussian‐DK. Observing that inconsistencies are mainly caused by camera imaging, we represent a consistent radiance field of the physical world using a set of anisotropic 3D Gaussians, and design a camera response module to compensate for multi‐view inconsistencies. We also introduce a step‐based gradient scaling strategy to constrain Gaussians near the camera, which turn out to be floaters, from splitting and cloning. Experiments on our proposed benchmark dataset demonstrate that Gaussian‐DK produces high‐quality renderings without ghosting and floater artifacts and significantly outperforms existing methods. Furthermore, we can also synthesize light‐up images by controlling exposure levels that clearly show details in shadow areas.
Förderung
- Beijing Science and Technology Planning Project
Zitieren
APA
Ye, S., Dong, Z., Hu, Y., Wen, Y., & Liu, Y. (2024). Gaussian in the Dark: Real‐Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting. Computer Graphics Forum, 43(7). https://doi.org/10.1111/cgf.15213
Vancouver
Ye S, Dong Z, Hu Y, Wen Y, Liu Y. Gaussian in the Dark: Real‐Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting. Computer Graphics Forum. 2024;43(7). doi:10.1111/cgf.15213
BibTeX
@article{Ye2024,
author = {Ye, Sheng and Dong, Zhen‐Hui and Hu, Yubin and Wen, Yu‐Hui and Liu, Yong‐Jin},
title = {Gaussian in the Dark: Real‐Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting},
journal = {Computer Graphics Forum},
year = {2024},
volume = {43},
number = {7},
doi = {10.1111/cgf.15213}
}
EUVIMED