From Few to Full: High-Resolution 3D Object Reconstruction from Sparse Views and Unknown Poses

Simple item page
dc.contributor.authorYao, Grekouen_US
dc.contributor.authorMavromatis, Sebastienen_US
dc.contributor.authorMari, Jean-Lucen_US
dc.contributor.editorLiu, Lingjieen_US
dc.contributor.editorAverkiou, Melinosen_US
dc.date.accessioned2024-04-30T08:21:16Z
dc.date.available2024-04-30T08:21:16Z
dc.date.issued2024
dc.description.abstractRecent progress in 3D reconstruction has been driven by generative models, moving from traditional multi-view dependence to single-image diffusion model based techniques. However, these innovative approaches often face challenges with sparse view scenarios, requiring known poses or template shapes, often failing in high-resolution reconstructions. Addressing these issues, we introduce the ''F2F'' (Few to Full) framework, designed for crafting high-resolution 3D models from few views and unknown camera poses, creating fully realistic 3D objects without external constraints. F2F employs a hybrid approach, optimizing both implicit and explicit representations through a unique pipeline involving a pretrained diffusion model for pose estimation, a deformable tetrahedra grid for feature volume construction, and an MLP (neural network) for surface optimization. Our method sets a new standard by ensuring surface geometry, topology, and semantic consistency through differentiable rendering, aiming for a comprehensive solution in 3D reconstruction from sparse views.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationEurographics 2024 - Posters
dc.identifier.doi10.2312/egp.20241045
dc.identifier.isbn978-3-03868-239-4
dc.identifier.issn1017-4656
dc.identifier.pages2 pages
dc.identifier.urihttps://doi.org/10.2312/egp.20241045
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/egp20241045
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 → Sparse views; 3D reconstruction; Hybrid 3D representation; Differentiable rendering
dc.subjectComputing methodologies → Sparse views
dc.subject3D reconstruction
dc.subjectHybrid 3D representation
dc.subjectDifferentiable rendering
dc.titleFrom Few to Full: High-Resolution 3D Object Reconstruction from Sparse Views and Unknown Posesen_US
Files
Original bundle
Now showing 1 - 3 of 3
No Thumbnail Available
Name:
10_egp20241045.pdf
Size:
624.55 KB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
EG2024_PPT_Grekou.pdf
Size:
1001.62 KB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
EG2024_PPT_Grekou.pptx
Size:
13.87 MB
Format:
Microsoft Powerpoint XML
Download
Collections
EG 2024 - Posters