PixOOD: Pixel-Level Out-of-Distribution Detection

1 code implementation • 30 May 2024 • Tomáš Vojíř, Jan Šochman, Jiří Matas

We propose a dense image prediction out-of-distribution detection algorithm, called PixOOD, which does not require training on samples of anomalous data and is not designed for a specific application which avoids traditional training biases.

Monocular Arbitrary Moving Object Discovery and Segmentation

1 code implementation • The 32nd British Machine Vision Conference 2021 • Michal Neoral, Jan Šochman, Jiří Matas

We propose a method for discovery and segmentation of objects that are, or their parts are, independently moving in the scene.

Motion Segmentation Object +3

Continual Occlusions and Optical Flow Estimation

no code implementations • 5 Nov 2018 • Michal Neoral, Jan Šochman, Jiří Matas

We show that providing occlusion masks as an additional input to flow estimation improves the standard performance metric by more than 25\% on both KITTI and Sintel.

Occlusion Estimation Optical Flow Estimation