izpis_h1_title_alt

Reconstructing superquadrics from intensity and color images
ID Tomašević, Darian (Avtor), ID Peer, Peter (Avtor), ID Solina, Franc (Avtor), ID Jaklič, Aleš (Avtor), ID Štruc, Vitomir (Avtor)

.pdfPDF - Predstavitvena datoteka, prenos (17,96 MB)
MD5: E24083484C4E2C44F66CDF72DE919CC5
URLURL - Izvorni URL, za dostop obiščite https://www.mdpi.com/1424-8220/22/14/5332 Povezava se odpre v novem oknu

Izvleček
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.

Jezik:Angleški jezik
Ključne besede:superquadrics, reconstruction, color images, deep learning, convolutional neural networks
Vrsta gradiva:Članek v reviji
Tipologija:1.01 - Izvirni znanstveni članek
Organizacija:FRI - Fakulteta za računalništvo in informatiko
FE - Fakulteta za elektrotehniko
Status publikacije:Objavljeno
Različica publikacije:Objavljena publikacija
Leto izida:2022
Št. strani:26 str.
Številčenje:Vol. 22, iss. 14, art. 5332
PID:20.500.12556/RUL-145182 Povezava se odpre v novem oknu
UDK:004.93
ISSN pri članku:1424-8220
DOI:10.3390/s22145332 Povezava se odpre v novem oknu
COBISS.SI-ID:115598595 Povezava se odpre v novem oknu
Datum objave v RUL:12.04.2023
Število ogledov:304
Število prenosov:55
Metapodatki:XML RDF-CHPDL DC-XML DC-RDF
:
Kopiraj citat
Objavi na:Bookmark and Share

Gradivo je del revije

Naslov:Sensors
Skrajšan naslov:Sensors
Založnik:MDPI
ISSN:1424-8220
COBISS.SI-ID:10176278 Povezava se odpre v novem oknu

Licence

Licenca:CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
Povezava:http://creativecommons.org/licenses/by/4.0/deed.sl
Opis:To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

Jezik:Slovenski jezik
Ključne besede:superkvadriki, rekonstrukcija, barvne slike, globoko učenje, konvolucijske nevronske mreže

Projekti

Financer:ARRS - Agencija za raziskovalno dejavnost Republike Slovenije
Številka projekta:J2-9228
Naslov:Segmentacija in rekonstrukcija superkvadričnih modelov iz 3D podatkov s pomočjo nevronske mreže

Financer:ARRS - Agencija za raziskovalno dejavnost Republike Slovenije
Številka projekta:P2-0214
Naslov:Računalniški vid

Financer:ARRS - Agencija za raziskovalno dejavnost Republike Slovenije
Številka projekta:P2-0250
Naslov:Metrologija in biometrični sistemi

Podobna dela

Podobna dela v RUL:
Podobna dela v drugih slovenskih zbirkah:

Nazaj