no code implementations • 4 May 2023 • Elena Kosheleva, Sunil Jaiswal, Faranak Shamsafar, Noshaba Cheema, Klaus Illgner-Fehns, Philipp Slusallek
As a benefit of using stereo inputs, a left-right consistency loss is introduced to improve the performance.
no code implementations • 17 Apr 2023 • Faranak Shamsafar, Sunil Jaiswal, Benjamin Kelkel, Kireeti Bodduna, Klaus Illgner-Fehns
Printed circuit boards (PCBs) are essential components of electronic devices, and ensuring their quality is crucial in their production.
1 code implementation • 24 Nov 2021 • Faranak Shamsafar, Andreas Zell
Stereo vision is an effective technique for depth estimation with broad applicability in autonomous urban and highway driving.
Ranked #1 on Stereo Depth Estimation on KITTI2015 (D1-all All metric)
1 code implementation • 23 Aug 2021 • Rafia Rahim, Faranak Shamsafar, Andreas Zell
In this work first, we show that these 3D convolutions in stereo networks consume up to 94% of overall network operations and act as a major bottleneck.
3 code implementations • 22 Aug 2021 • Faranak Shamsafar, Samuel Woerz, Rafia Rahim, Andreas Zell
Depending on the dimension of cost volume, we design a 2D and a 3D model with encoder-decoders built from 2D and 3D convolutions, respectively.
Ranked #1 on Stereo Depth Estimation on sceneflow
no code implementations • 15 Jun 2021 • Timon Höfer, Faranak Shamsafar, Nuri Benbarka, Andreas Zell
Bin picking is a core problem in industrial environments and robotics, with its main module as 6D pose estimation.