PartFull: A Hybrid Method for Part-Aware 3D Object Reconstruction from Sparse Views

Simple item page
dc.contributor.authorYao, Grekouen_US
dc.contributor.authorMavromatis, Sébastienen_US
dc.contributor.authorMari, Jean-Lucen_US
dc.contributor.editorCeylan, Duyguen_US
dc.contributor.editorLi, Tzu-Maoen_US
dc.date.accessioned2025-05-09T09:36:40Z
dc.date.available2025-05-09T09:36:40Z
dc.date.issued2025
dc.description.abstractRecent advancements in 3D object reconstruction have been significantly enhanced by generative models; however, challenges remain when detailed 3D shapes are reconstructed from limited, sparse views. Traditional methods often require multiple input views and known camera poses, whereas newer approaches that leverage diffusion models from single images encounter realworld data limitations. In response, we propose ''PartFull'', a novel framework for part-aware 3D reconstruction using a hybrid approach. ''PartFull'' generates realistic 3D models from sparse RGB images by combining implicit and explicit representations to optimize surface reconstruction. Starting with sketch-based 3D models from individual views, these models are fused into a coherent object. Our pipeline incorporates a pretrained latent space for part-aware implicit representations and a deformable grid for feature volume construction and surface optimization. PartFull's joint optimization of surface geometry, topology, and implicit part segmentation constitutes a new approach to addressing the challenges of 3D reconstruction from sparse views.en_US
dc.description.sectionheadersShort Paper 5
dc.description.seriesinformationEurographics 2025 - Short Papers
dc.identifier.doi10.2312/egs.20251053
dc.identifier.isbn978-3-03868-268-4
dc.identifier.issn1017-4656
dc.identifier.pages4 pages
dc.identifier.urihttps://doi.org/10.2312/egs.20251053
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/egs20251053
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; Implicit part-aware geometry learning;
dc.subjectComputing methodologies → Sparse views
dc.subject3D reconstruction
dc.subjectHybrid 3D representation
dc.subjectImplicit part
dc.subjectaware geometry learning
dc.titlePartFull: A Hybrid Method for Part-Aware 3D Object Reconstruction from Sparse Viewsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
egs20251053.pdf
Size:
608.59 KB
Format:
Adobe Portable Document Format
Download
Collections
EG 2025 - Short Papers