Search Results for author: Patrick Knöbelreiter

Found 9 papers, 3 papers with code

InfoSeg: Unsupervised Semantic Image Segmentation with Mutual Information Maximization

no code implementations7 Oct 2021 Robert Harb, Patrick Knöbelreiter

We propose a novel method for unsupervised semantic image segmentation based on mutual information maximization between local and global high-level image features.

 Ranked #1 on Unsupervised Semantic Segmentation on Potsdam-3 (Pixel Accuracy metric)

Image Segmentation Representation Learning +1

BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo

no code implementations23 Oct 2020 Christian Sormann, Patrick Knöbelreiter, Andreas Kuhn, Mattia Rossi, Thomas Pock, Friedrich Fraundorfer

We therefore show how we can calculate a normalization based on the expected 3D error, which we can then use to normalize the label jumps in the CRF.

Frame-To-Frame Consistent Semantic Segmentation

1 code implementation3 Aug 2020 Manuel Rebol, Patrick Knöbelreiter

In this work, we aim for temporally consistent semantic segmentation throughout frames in a video.

Segmentation Semantic Segmentation

Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems

1 code implementation13 Mar 2020 Patrick Knöbelreiter, Christian Sormann, Alexander Shekhovtsov, Friedrich Fraundorfer, Thomas Pock

It has been proposed by many researchers that combining deep neural networks with graphical models can create more efficient and better regularized composite models.

Optical Flow Estimation Semantic Segmentation

Learned Collaborative Stereo Refinement

no code implementations31 Jul 2019 Patrick Knöbelreiter, Thomas Pock

The proposed variational network arises naturally from unrolling the iterates of a proximal gradient method applied to a variational energy defined in a joint disparity, color, and confidence image space.

Rolling Shutter Correction

Self-Supervised Learning for Stereo Reconstruction on Aerial Images

no code implementations29 Jul 2019 Patrick Knöbelreiter, Christoph Vogel, Thomas Pock

Recent developments established deep learning as an inevitable tool to boost the performance of dense matching and stereo estimation.

Self-Supervised Learning

Learning Energy Based Inpainting for Optical Flow

1 code implementation9 Nov 2018 Christoph Vogel, Patrick Knöbelreiter, Thomas Pock

Modern optical flow methods are often composed of a cascade of many independent steps or formulated as a black box neural network that is hard to interpret and analyze.

feature selection Optical Flow Estimation

Scalable Full Flow with Learned Binary Descriptors

no code implementations20 Jul 2017 Gottfried Munda, Alexander Shekhovtsov, Patrick Knöbelreiter, Thomas Pock

We tackle the computation- and memory-intensive operations on the 4D cost volume by a min-projection which reduces memory complexity from quadratic to linear and binary descriptors for efficient matching.

Optical Flow Estimation

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