Darian Tomašević (Author), Peter Peer (Author), Franc Solina (Author), Aleš Jaklič (Author), Vitomir Štruc (Author)

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

superkvadriki;rekonstrukcija;barvne slike;globoko učenje;konvolucijske nevronske mreže;superquadrics;reconstruction;color images;deep learning;convolutional neural networks;

Data

Language: English
Year of publishing:
Typology: 1.01 - Original Scientific Article
Organization: UL FRI - Faculty of Computer and Information Science
UDC: 004.93
COBISS: 115598595 Link will open in a new window
ISSN: 1424-8220
Views: 24
Downloads: 4
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: Slovenian
Secondary keywords: superkvadriki;rekonstrukcija;barvne slike;globoko učenje;konvolucijske nevronske mreže;
Type (COBISS): Article
Pages: str. 1-27
Volume: ǂVol. ǂ22
Issue: ǂiss. ǂ14
Chronology: Jul. 2022
DOI: 10.3390/s22145332
ID: 18572680