High-Quality Geometry and Texture Editing of Neural Radiance Field

Simple item page
dc.contributor.authorKim, Soongjinen_US
dc.contributor.authorSon, Jooeunen_US
dc.contributor.authorJu, Gwangjinen_US
dc.contributor.authorLee, Joo Hoen_US
dc.contributor.authorLee, Seungyongen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:05:36Z
dc.date.available2024-10-13T18:05:36Z
dc.date.issued2024
dc.description.abstractRecent advances in Neural Radiance Field (NeRF) have demonstrated impressive rendering quality reconstructed from input images. However, the density-based radiance field representation introduces entanglement of geometry and texture, limiting the editability. To address this issue, NeuMesh proposed a mesh-based NeRF editing method supporting deformation and texture editing. Still, it fails reconstructing and rendering fine details of input images, and the dependency between rendering scheme and geometry limits editability for target scenes. In this paper, we propose an intermediate scene representation where a near-surface volume is associated with the guide mesh. Our key idea is separating a given scene into geometry, parameterized texture space, and radiance field. We define a mapping between GHI-coordinate space and DE-coordinate system defined by combination of mesh parameterization and the height from mesh surface to efficiently encode the near-surface volume. With the surface-aligned radiance field defined in the near-surface volume, our method can generate high quality rendering results with high frequency details. Our method also supports various geometry and appearance editing operations while preserving high rendering quality. We demonstrate the performance of our method by comparing it with the state-of-the-art methods both qualitatively and quantitatively and show its applications including shape deformation, texture filling, and texture painting.en_US
dc.description.sectionheadersNeural Radiance Fields and Gaussian Splatting
dc.description.seriesinformationPacific Graphics Conference Papers and Posters
dc.identifier.doi10.2312/pg.20241318
dc.identifier.isbn978-3-03868-250-9
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20241318
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20241318
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->Image-based rendering
dc.subjectComputing methodologies
dc.subjectImage
dc.subjectbased rendering
dc.titleHigh-Quality Geometry and Texture Editing of Neural Radiance Fielden_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
pg20241318.pdf
Size:
7.46 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1473_mm.mp4
Size:
93.85 MB
Format:
Video MP4
Download
Thumbnail Image
Name:
paper1473_mm.pdf
Size:
138.79 KB
Format:
Adobe Portable Document Format
Download
Collections
PG2024 Conference Papers and Posters