Gaussian in the Dark: Real-Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting

Simple item page
dc.contributor.authorYe, Shengen_US
dc.contributor.authorDong, Zhen-Huien_US
dc.contributor.authorHu, Yubinen_US
dc.contributor.authorWen, Yu-Huien_US
dc.contributor.authorLiu, Yong-Jinen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:07:35Z
dc.date.available2024-10-13T18:07:35Z
dc.date.issued2024
dc.description.abstract3D 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.en_US
dc.description.number7
dc.description.sectionheaders3D Reconstruction and Novel View Synthesis II
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15213
dc.identifier.issn1467-8659
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15213
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15213
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Rendering; Computational photography
dc.subjectComputing methodologies → Rendering
dc.subjectComputational photography
dc.titleGaussian in the Dark: Real-Time View Synthesis From Inconsistent Dark Images Using Gaussian Splattingen_US
Files
Original bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
cgf15213.pdf
Size:
15.43 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1005_mm.mp4
Size:
21.57 MB
Format:
Video MP4
Download
Collections
43-Issue 7