Neural Impostor: Editing Neural Radiance Fields with Explicit Shape Manipulation

Simple item page
dc.contributor.authorLiu, Ruiyangen_US
dc.contributor.authorXiang, Jinxuen_US
dc.contributor.authorZhao, Bowenen_US
dc.contributor.authorZhang, Ranen_US
dc.contributor.authorYu, Jingyien_US
dc.contributor.authorZheng, Changxien_US
dc.contributor.editorChaine, Raphaëlleen_US
dc.contributor.editorDeng, Zhigangen_US
dc.contributor.editorKim, Min H.en_US
dc.date.accessioned2023-10-09T07:38:20Z
dc.date.available2023-10-09T07:38:20Z
dc.date.issued2023
dc.description.abstractNeural Radiance Fields (NeRF) have significantly advanced the generation of highly realistic and expressive 3D scenes. However, the task of editing NeRF, particularly in terms of geometry modification, poses a significant challenge. This issue has obstructed NeRF's wider adoption across various applications. To tackle the problem of efficiently editing neural implicit fields, we introduce Neural Impostor, a hybrid representation incorporating an explicit tetrahedral mesh alongside a multigrid implicit field designated for each tetrahedron within the explicit mesh. Our framework bridges the explicit shape manipulation and the geometric editing of implicit fields by utilizing multigrid barycentric coordinate encoding, thus offering a pragmatic solution to deform, composite, and generate neural implicit fields while maintaining a complex volumetric appearance. Furthermore, we propose a comprehensive pipeline for editing neural implicit fields based on a set of explicit geometric editing operations. We show the robustness and adaptability of our system through diverse examples and experiments, including the editing of both synthetic objects and real captured data. Finally, we demonstrate the authoring process of a hybrid synthetic-captured object utilizing a variety of editing operations, underlining the transformative potential of Neural Impostor in the field of 3D content creation and manipulation.en_US
dc.description.number7
dc.description.sectionheadersRadiance and Appearance
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume42
dc.identifier.doi10.1111/cgf.14981
dc.identifier.issn1467-8659
dc.identifier.pages19 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14981
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14981
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies -> Rendering; Appearance and texture representations; Image-based rendering
dc.subjectComputing methodologies
dc.subjectRendering
dc.subjectAppearance and texture representations
dc.subjectImage
dc.subjectbased rendering
dc.titleNeural Impostor: Editing Neural Radiance Fields with Explicit Shape Manipulationen_US
Files
Original bundle
Now showing 1 - 3 of 3
No Thumbnail Available
Name:
v42i7_53_14981.pdf
Size:
109.61 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1226_mm.mp4
Size:
629.42 MB
Format:
Unknown data format
Download
No Thumbnail Available
Name:
paper1226_mm.mp4
Size:
629.42 MB
Format:
Unknown data format
Download
Collections
42-Issue 7