Search Results for author: Tim Oblak

Found 2 papers, 0 papers with code

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.

Recovery of Superquadrics from Range Images using Deep Learning: A Preliminary Study

no code implementations13 Apr 2019 Tim Oblak, Klemen Grm, Aleš Jaklič, Peter Peer, Vitomir Štruc, Franc Solina

It has been a longstanding goal in computer vision to describe the 3D physical space in terms of parameterized volumetric models that would allow autonomous machines to understand and interact with their surroundings.

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