Hubert Żabiński

Hubert Żabiński

Auto-generated profile, based on publicly available information

Hubert Żabiński

Institute of Multimedia Telecommunications, Poznan University of Technology, and Mucha Sp. z o.o.,Pozna,Poland

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 October 2026 in SoftwareX
Verified
Journal Article
Closed access
AGAdam Grzelka
Adam Grzelka
JSJakub Stankowski
Jakub Stankowski
KKKrzysztof Klimaszewski
Krzysztof Klimaszewski
HŻHubert Żabiński
Hubert Żabiński

26 September 2023
Verified
Conference Paper
Closed access
HŻHubert Żabiński
Hubert Żabiński
KWKrzysztof Wegner
Krzysztof Wegner
OSOlgierd Stankiewicz
Olgierd Stankiewicz
Fast algorithms for stereoscopic depth estimation typically employ processing of the input images in a Single Scanning Order (SSO). In this paper we present a novel approach that employs processing in Multiple Scanning Orders (MSO), which are then merged together into a final depth map. We demonstrate the advantages of the proposal on the example of a fast depth estimation technique [1], adaptable both for mobile platforms and FPGA. We show that application of the proposal leads to considerable quality improvement at an acceptable complexity cost.

20 September 2021
Verified
Conference Paper
Closed access
HZHubert Zabinski
Hubert Zabinski
OSOlgierd Stankiewicz
Olgierd Stankiewicz
Correspondence matching is a prerequisite step in dense depth estimation techniques. In this paper we consider various similarity metrics for correspondence matching and we present an approach which can be used to optimize it. Experimental results show that by careful selection of similarity metric can have positive impact on depth estimation quality and that the differences between various metrics range up to 60 percent points of bad-pixel depth map quality ratio. It has also been shown that usage of proposed composite similarity can lead to improved depth map quality, expressed as lower bad-pixel ratio.