Im2SurfTex: Surface Texture Generation via Neural Backprojection of Multi-View Images

dc.contributor.authorGeorgiou, Yiangosen_US
dc.contributor.authorLoizou, Mariosen_US
dc.contributor.authorAverkiou, Melinosen_US
dc.contributor.authorKalogerakis, Evangelosen_US
dc.contributor.editorAttene, Marcoen_US
dc.contributor.editorSellán, Silviaen_US
dc.date.accessioned2025-06-20T07:39:54Z
dc.date.available2025-06-20T07:39:54Z
dc.date.issued2025
dc.description.abstractWe present Im2SurfTex, a method that generates textures for input 3D shapes by learning to aggregate multi-view image outputs produced by 2D image diffusion models onto the shapes' texture space. Unlike existing texture generation techniques that use ad hoc backprojection and averaging schemes to blend multiview images into textures, often resulting in texture seams and artifacts, our approach employs a trained neural module to boost texture coherency. The key ingredient of our module is to leverage neural attention and appropriate positional encodings of image pixels based on their corresponding 3D point positions, normals, and surface-aware coordinates as encoded in geodesic distances within surface patches. These encodings capture texture correlations between neighboring surface points, ensuring better texture continuity. Experimental results show that our module improves texture quality, achieving superior performance in high-resolution texture generation.en_US
dc.description.number5
dc.description.sectionheadersShape Segmentation and Texturing
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70191
dc.identifier.issn1467-8659
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70191
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70191
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Texturing; Neural networks
dc.subjectComputing methodologies → Texturing
dc.subjectNeural networks
dc.titleIm2SurfTex: Surface Texture Generation via Neural Backprojection of Multi-View Imagesen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
cgf70191.pdf
Size:
20.58 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
fp1-1020_mm.zip
Size:
526 MB
Format:
Zip file
Collections