Reconstructing Superquadrics from Intensity and Color Images
Open Access
Abstract
The task of reconstructing 3D scenes based on visual data represents a longstanding problem in computer vision. Common reconstruction approaches rely on the use of multiple volumetric primitives to describe complex objects. Superquadrics (a class of volumetric primitives) have shown great promise due to their ability to describe various shapes with only a few parameters. Recent research has shown that deep learning methods can be used to accurately reconstruct random superquadrics from both 3D point cloud data and simple depth images. In this paper, we extended these reconstruction methods to intensity and color images. Specifically, we used a dedicated convolutional neural network (CNN) model to reconstruct a single superquadric from the given input image. We analyzed the results in a qualitative and quantitative manner, by visualizing reconstructed superquadrics as well as observing error and accuracy distributions of predictions. We showed that a CNN model designed around a simple ResNet backbone can be used to accurately reconstruct superquadrics from images containing one object, but only if one of the spatial parameters is fixed or if it can be determined from other image characteristics, e.g., shadows. Furthermore, we experimented with images of increasing complexity, for example, by adding textures, and observed that the results degraded only slightly. In addition, we show that our model outperforms the current state-of-the-art method on the studied task. Our final result is a highly accurate superquadric reconstruction model, which can also reconstruct superquadrics from real images of simple objects, without additional training.Keywords
Funding Information
- The Slovenian Research and Innovation Agency (J2-9228 (B), P2-0214 (B))
This publication has 46 references indexed in Scilit:
- Volumetric models from 3D point clouds: The case study of sarcophagi cargo from a 2nd/3rd century AD Roman shipwreck near Sutivan on island Brač, CroatiaJournal of Archaeological Science, 2015
- Practical Recommendations for Gradient-Based Training of Deep Architectures2012
- Part-level object recognition using superquadricsComputer Vision and Image Understanding, 2004
- Superquadrics for segmenting and modeling range dataIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Darboux frames, snakes, and super-quadrics: geometry from the bottom upIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993
- UNIFORM RANDOM ROTATIONS1992
- Dynamic 3D models with local and global deformations: deformable superquadricsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- Recovery of parametric models from range images: the case for superquadrics with global deformationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Hyperquadrics: Smoothly deformable shapes with convex polyhedral boundsComputer Vision, Graphics, and Image Processing, 1988
- Perceptual organization and the representation of natural formArtificial Intelligence, 1986