Search Results for author: Jaka Šircelj

Found 2 papers, 0 papers with code

Hierarchical Superquadric Decomposition with Implicit Space Separation

no code implementations15 Sep 2022 Jaka Šircelj, Peter Peer, Franc Solina, Vitomir Štruc

We introduce a new method to reconstruct 3D objects using a set of volumetric primitives, i. e., superquadrics.

Object

Segmentation and Recovery of Superquadric Models using Convolutional Neural Networks

no code implementations28 Jan 2020 Jaka Šircelj, Tim Oblak, Klemen Grm, Uroš Petković, Aleš Jaklič, Peter Peer, Vitomir Štruc, Franc Solina

In this paper we address the problem of representing 3D visual data with parameterized volumetric shape primitives.

Cannot find the paper you are looking for? You can Submit a new open access paper.