CAP-UDF: Learning Unsigned Distance Functions Progressively From Raw Point Clouds With Consistency-Aware Field Optimization
- 22 April 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (12) , 7475-7492
Abstract
Surface reconstruction for point clouds is an important task in 3D computer vision. Most of the latest methods resolve this problem by learning signed distance functions from point clouds, which are limited to reconstructing closed surfaces. Some other methods tried to represent open surfaces using unsigned distance functions (UDF) which are learned from ground truth distances. However, the learned UDF is hard to provide smooth distance fields due to the discontinuous character of point clouds. In this paper, we propose CAP-UDF, a novel method to learn consistency-aware UDF from raw point clouds. We achieve this by learning to move queries onto the surface with a field consistency constraint, where we also enable to progressively estimate a more accurate surface. Specifically, we train a neural network to gradually infer the relationship between queries and the approximated surface by searching for the moving target of queries in a dynamic way. Meanwhile, we introduce a polygonization algorithm to extract surfaces using the gradients of the learned UDF. We conduct comprehensive experiments in surface reconstruction for point clouds, real scans or depth maps, and further explore our performance in unsupervised point normal estimation, which demonstrate non-trivial improvements of CAP-UDF over the state-of-the-art methods.Keywords
Funding Information
- National Key R&D Program of China (2022YFC3800600)
- National Natural Science Foundation of China (62272263, 62072268)
This publication has 73 references indexed in Scilit:
- Multi-grid representation with field regularization for self-supervised surface reconstruction from point cloudsComputers & Graphics, 2023
- MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks2022
- Latent Partition Implicit with Surface Codes for 3D Representation2022
- Convolutional Occupancy Networks2020
- Curriculum DeepSDF2020
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares2020
- PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations2020
- Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction2020
- Principal component analysisWIREs Computational Statistics, 2010