Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations
METADATA ONLY
Loading...
Author / Producer
Date
2021
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
Neural implicit functions have emerged as a powerful representation for surfaces in 3D. Such a function can encode a high quality surface with intricate details into the parameters of a deep neural network. However, optimizing for the parameters for accurate and robust reconstructions remains a challenge, especially when the input data is noisy or incomplete. In this work, we develop a hybrid neural surface representation that allows us to impose geometry-aware sampling and regularization, which significantly improves the fidelity of reconstructions. We propose to use iso-points as an explicit representation for a neural implicit function. These points are computed and updated on-the-fly during training to capture important geometric features and impose geometric constraints on the optimization. We demonstrate that our method can be adopted to improve state-of-the-art techniques for reconstructing neural implicit surfaces from multi-view images or point clouds. Quantitative and qualitative evaluations show that, compared with existing sampling and optimization methods, our approach allows faster convergence, better generalization, and accurate recovery of details and topology.
Permanent link
Publication status
published
External links
Editor
Book title
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Journal / series
Volume
Pages / Article No.
374 - 383
Publisher
IEEE
Event
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Organisational unit
03911 - Sorkine Hornung, Olga / Sorkine Hornung, Olga