20.500.12556/RUL-145182 Reconstructing superquadrics from intensity and color images 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. superquadrics reconstruction color images deep learning convolutional neural networks superkvadriki rekonstrukcija barvne slike globoko učenje konvolucijske nevronske mreže true false true Angleški jezik Slovenski jezik Članek v reviji 2023-04-12 14:07:08 2023-04-12 14:07:09 2023-04-13 03:31:26 0000-00-00 00:00:00 2022 0 0 26 str. iss. 14, art. 5332 Vol. 22 Jul. 2022 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.93 1424-8220 10.3390/s22145332 115598595 sensors-22-05332-v3.pdf sensors-22-05332-v3.pdf 1 E24083484C4E2C44F66CDF72DE919CC5 b9600b8ddc24dc20f64ef6b9eb9abcbb4db9727651d6be99baefaa71d210cd66 b791d3e5-d92a-11ed-a314-00155dcfd717 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=167884 https://www.mdpi.com/1424-8220/22/14/5332 1 675aaaa8-d92a-11ed-a314-00155dcfd717 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=167883 Fakulteta za računalništvo in informatiko Fakulteta za elektrotehniko 0 0 0