Reconstructing superquadrics from intensity and color images

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

Povzetek

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.

Ključne besede

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

Podatki

Jezik:	Angleški jezik
Leto izida:	2022
Tipologija:	1.01 - Izvirni znanstveni članek
Organizacija:	UL FRI - Fakulteta za računalništvo in informatiko
UDK:	004.93
COBISS:	115598595
ISSN:	1424-8220
Št. ogledov:	24
Št. prenosov:	4
Ocena:	0 (0 glasov)
Metapodatki:

Ostali podatki

Sekundarni jezik:	Slovenski jezik
Sekundarne ključne besede:	superkvadriki;rekonstrukcija;barvne slike;globoko učenje;konvolucijske nevronske mreže;
Vrsta dela (COBISS):	Članek v reviji
Strani:	str. 1-27
Letnik:	ǂVol. ǂ22
Zvezek:	ǂiss. ǂ14
Čas izdaje:	Jul. 2022
DOI:	10.3390/s22145332
ID:	18572680