GaussianMatch: Adaptive Learning Continuous Surfaces for Light Field Depth Estimation

Simple item page
dc.contributor.authorSun, Zexinen_US
dc.contributor.authorChen, Rongshanen_US
dc.contributor.authorWang, Yuen_US
dc.contributor.authorCui, Zhenglongen_US
dc.contributor.authorYang, Daen_US
dc.contributor.authorLi, Siyangen_US
dc.contributor.authorHuang, Xuefeien_US
dc.contributor.authorSheng, Haoen_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorHan, Ping-Hsuanen_US
dc.contributor.editorLin, Shih-Syunen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorSchneider, Teseoen_US
dc.contributor.editorTsai, Hsin-Rueyen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.contributor.editorZhang, Eugeneen_US
dc.date.accessioned2025-10-07T06:03:55Z
dc.date.available2025-10-07T06:03:55Z
dc.date.issued2025
dc.description.abstractLight field (LF) depth estimation plays a vital role in computational imaging by reconstructing 3D structures from multiple viewpoints. However, images are merely discrete expressions of scenes due to the resolution constraints of cameras, leading to depth discontinuities and outliers-particularly in textureless or occluded regions, degrading reconstruction coherence. To address the challenges mentioned above, we propose GaussianMatch, a probabilistic depth estimation framework that models per-pixel depth as a learnable Gaussian distribution in continuous space. This scheme effectively alleviates the discretization problem of LF images by adaptively reconstructing continuous surfaces, while enabling uncertainty-aware optimization.Furthermore, the framework naturally fuses information among adjacent pixels and adapts each Gaussian's variance according to scene complexity, achieving robustness in both texture-rich and ambiguous regions. We further design GaussianNet, which regresses per-pixel Gaussian parameters and generates the final depth map via Gaussian accumulation. Extensive experiments on multiple LF benchmarks demonstrate that GaussianNet achieves state-of-the-art accuracy, with significant improvements in handling depth discontinuities and occlusions.en_US
dc.description.sectionheadersPoint Clouds & Gaussian Splatting
dc.description.seriesinformationPacific Graphics Conference Papers, Posters, and Demos
dc.identifier.doi10.2312/pg.20251283
dc.identifier.isbn978-3-03868-295-0
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20251283
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20251283
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Matching; Epipolar geometry; Computational photography; Image representations
dc.subjectComputing methodologies → Matching
dc.subjectEpipolar geometry
dc.subjectComputational photography
dc.subjectImage representations
dc.titleGaussianMatch: Adaptive Learning Continuous Surfaces for Light Field Depth Estimationen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pg20251283.pdf
Size:
2.83 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2025 Conference Papers, Posters, and Demos