Stop Thinking, Just Do!

Sungsoo Kim's Blog

Learning Local Geometric Descriptors from RGB-D Reconstructions

tagsTags

28 April 2017


3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions

  • Authors: Andy Zeng, Shuran Song, Matthias Nießner, Matthew Fisher, Jianxiong Xiao, and Thomas Funkhouser
  • Publications: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 Oral Presentation

Abstract

Matching local geometric features on real-world depth images is a challenging task due to the noisy, low-resolution, and incomplete nature of 3D scan data. These difficulties limit the performance of current state-of-art methods, which are typically based on histograms over geometric properties. In this paper, we present 3DMatch, a data-driven model that learns a local volumetric patch descriptor for establishing correspondences between partial 3D data. To amass training data for our model, we propose an unsupervised feature learning method that leverages the millions of correspondence labels found in existing RGB-D reconstructions. Experiments show that our descriptor is not only able to match local geometry in new scenes for reconstruction, but also generalize to different tasks and spatial scales (e.g. instance-level object model alignment for the Amazon Picking Challenge, and mesh surface correspondence). Results show that 3DMatch consistently outperforms other state-of-the-art approaches by a significant margin.

Overview

From existing RGB-D reconstructions (a), we extract local 3D patches and correspondence labels from scans of different views (b). We collect pairs of matching and non-matching local 3D patches converted into a volumetric representation (c) to train a 3D ConvNet-based descriptor (d). This geometric descriptor can be used to establish correspondences for matching 3D geometry in various applications (e) such as reconstruction, model alignment, and surface correspondence.

Paper

Video

Code

All 3DMatch code (for training and testing) can be found in our Github repository here.

References

[1] 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions, Princeton University, 2017.


comments powered by Disqus