DeepFit : 3D Surface Fitting via Neural Network Weighted Least Squares (ECCV 2020 Oral) - 2 minutes

ECCV 2020

DeepFit : 3D Surface Fitting via Neural Network Weighted Least Squares (ECCV 2020 Oral) - 2 minutes

Aug 18, 2020
|
37 views
|
Details
Paper: https://arxiv.org/abs/2003.10826 Code: https://github.com/sitzikbs/DeepFit Long version: https://youtu.be/PrlFen2BuaU DeepFit : 3D Surface Fitting via Neural Network Weighted Least Squares Oral presentation at European Conference on Computer Vision (ECCV), 2020 Abstract: We propose a surface fitting method for unstructured 3D point clouds. This method, called DeepFit, incorporates a neural network to learn point-wise weights for weighted least squares polynomial surface fitting. The learned weights act as a soft selection for the neighbourhood of surface points thus avoiding the scale selection required of previous methods. To train the network we propose a novel surface consistency loss that improves point weight estimation. The method enables extracting normal vectors and other geometrical properties, such as principal curvatures, the latter were not presented as ground truth during training. We achieve state-of-the-art results on a benchmark normal and curvature estimation dataset, demonstrate robustness to noise, outliers and density variations, and show its application on noise removal. More research by Yizhak Ben-Shabat (Itzik): http://www.itzikbs.com

Comments
loading...