Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/180249
Title: ClusteringSDF: self-organized neural implicit surfaces for 3D decomposition
Authors: Wu, Tianhao
Zheng, Chuanxia
Cham, Tat-Jen
Wu, Qianyi
Keywords: Computer and Information Science
Issue Date: 2024
Source: Wu, T., Zheng, C., Cham, T. & Wu, Q. (2024). ClusteringSDF: self-organized neural implicit surfaces for 3D decomposition. 2024 European Conference on Computer Vision (ECCV). https://dx.doi.org/10.48550/arXiv.2403.14619
Conference: 2024 European Conference on Computer Vision (ECCV)
Abstract: 3D decomposition/segmentation still remains a challenge as large-scale 3D annotated data is not readily available. Contemporary approaches typically leverage 2D machine-generated segments, integrating them for 3D consistency. While the majority of these methods are based on NeRFs, they face a potential weakness that the instance/semantic embedding features derive from independent MLPs, thus preventing the segmentation network from learning the geometric details of the objects directly through radiance and density. In this paper, we propose ClusteringSDF, a novel approach to achieve both segmentation and reconstruction in 3D via the neural implicit surface representation, specifically Signal Distance Function (SDF), where the segmentation rendering is directly integrated with the volume rendering of neural implicit surfaces. Although based on ObjectSDF++, ClusteringSDF no longer requires the ground-truth segments for supervision while maintaining the capability of reconstructing individual object surfaces, but purely with the noisy and inconsistent labels from pre-trained models.As the core of ClusteringSDF, we introduce a high-efficient clustering mechanism for lifting the 2D labels to 3D and the experimental results on the challenging scenes from ScanNet and Replica datasets show that ClusteringSDF can achieve competitive performance compared against the state-of-the-art with significantly reduced training time.
URI: https://hdl.handle.net/10356/180249
URL: http://arxiv.org/abs/2403.14619v1
DOI: 10.48550/arXiv.2403.14619
DOI (Related Dataset): 10.21979/N9/RJUHMC
Schools: College of Computing and Data Science 
Research Centres: S-Lab
Rights: © 2024 ECCV. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:CCDS Conference Papers

Files in This Item:
File Description SizeFormat 
ClusteringSDF Self-Organized Neural Implicit Surfaces for 3D Decomposition.pdfPreprint11.61 MBAdobe PDFView/Open

Page view(s)

55
Updated on Dec 4, 2024

Download(s)

6
Updated on Dec 4, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.