Search Results for author: Horst Bischof

Found 60 papers, 18 papers with code

OctNetFusion: Learning Depth Fusion from Data

1 code implementation4 Apr 2017 Gernot Riegler, Ali Osman Ulusoy, Horst Bischof, Andreas Geiger

In this paper, we present a learning based approach to depth fusion, i. e., dense 3D reconstruction from multiple depth images.

3D Reconstruction

Learning Pose Specific Representations by Predicting Different Views

2 code implementations CVPR 2018 Georg Poier, David Schinagl, Horst Bischof

To exploit this observation, we train a model that -- given input from one view -- estimates a latent representation, which is trained to be predictive for the appearance of the object when captured from another viewpoint.

Hand Pose Estimation Object

The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization

1 code implementation CVPR 2022 M. Jehanzeb Mirza, Jakub Micorek, Horst Possegger, Horst Bischof

This can be a hurdle in fields which require continuous dynamic adaptation or suffer from scarcity of data, e. g. autonomous driving in challenging weather conditions.

Autonomous Driving object-detection +3

An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions

1 code implementation19 Apr 2022 M. Jehanzeb Mirza, Marc Masana, Horst Possegger, Horst Bischof

This catastrophic forgetting is typically addressed via incremental learning approaches which usually re-train the model by either keeping a memory bank of training samples or keeping a copy of the entire model or model parameters for each scenario.

Autonomous Driving Incremental Learning +2

Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization

3 code implementations2 Aug 2019 Christian Payer, Darko Štern, Horst Bischof, Martin Urschler

In many medical image analysis applications, often only a limited amount of training data is available, which makes training of convolutional neural networks (CNNs) challenging.

regression

Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly

1 code implementation15 Jan 2018 Michael Opitz, Georg Waltner, Horst Possegger, Horst Bischof

To this end, we divide the last embedding layer of a deep network into an embedding ensemble and formulate training this ensemble as an online gradient boosting problem.

Image Retrieval Metric Learning +1

Video Test-Time Adaptation for Action Recognition

1 code implementation CVPR 2023 Wei Lin, Muhammad Jehanzeb Mirza, Mateusz Kozinski, Horst Possegger, Hilde Kuehne, Horst Bischof

Our proposed method demonstrates a substantial performance gain over existing test-time adaptation approaches in both evaluations of a single distribution shift and the challenging case of random distribution shifts.

Action Recognition Temporal Action Localization +1

MURAUER: Mapping Unlabeled Real Data for Label AUstERity

1 code implementation23 Nov 2018 Georg Poier, Michael Opitz, David Schinagl, Horst Bischof

In this work, we remove this requirement by learning to map from the features of real data to the features of synthetic data mainly using a large amount of synthetic and unlabeled real data.

3D Hand Pose Estimation

MATE: Masked Autoencoders are Online 3D Test-Time Learners

1 code implementation ICCV 2023 M. Jehanzeb Mirza, Inkyu Shin, Wei Lin, Andreas Schriebl, Kunyang Sun, Jaesung Choe, Horst Possegger, Mateusz Kozinski, In So Kweon, Kun-Jin Yoon, Horst Bischof

Our MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring in test data.

3D Object Classification Point Cloud Classification

ActMAD: Activation Matching to Align Distributions for Test-Time-Training

1 code implementation CVPR 2023 Muhammad Jehanzeb Mirza, Pol Jané Soneira, Wei Lin, Mateusz Kozinski, Horst Possegger, Horst Bischof

Test-Time-Training (TTT) is an approach to cope with out-of-distribution (OOD) data by adapting a trained model to distribution shifts occurring at test-time.

Image Classification

GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Data

1 code implementation ICCV 2023 David Schinagl, Georg Krispel, Christian Fruhwirth-Reisinger, Horst Possegger, Horst Bischof

Widely-used LiDAR-based 3D object detectors often neglect fundamental geometric information readily available from the object proposals in their confidence estimation.

Object

CycDA: Unsupervised Cycle Domain Adaptation from Image to Video

1 code implementation30 Mar 2022 Wei Lin, Anna Kukleva, Kunyang Sun, Horst Possegger, Hilde Kuehne, Horst Bischof

To address these challenges, we propose Cycle Domain Adaptation (CycDA), a cycle-based approach for unsupervised image-to-video domain adaptation by leveraging the joint spatial information in images and videos on the one hand and, on the other hand, training an independent spatio-temporal model to bridge the modality gap.

Action Recognition Domain Adaptation +1

TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification

1 code implementation13 Sep 2023 M. Jehanzeb Mirza, Leonid Karlinsky, Wei Lin, Horst Possegger, Rogerio Feris, Horst Bischof

Vision and Language Models (VLMs), such as CLIP, have enabled visual recognition of a potentially unlimited set of categories described by text prompts.

Zero-Shot Learning

Efficient Multi-Organ Segmentation Using SpatialConfiguration-Net with Low GPU Memory Requirements

1 code implementation26 Nov 2021 Franz Thaler, Christian Payer, Horst Bischof, Darko Stern

Even though many semantic segmentation methods exist that are able to perform well on many medical datasets, often, they are not designed for direct use in clinical practice.

Organ Segmentation Segmentation +1

Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions

1 code implementation30 May 2023 Stefan Leitner, M. Jehanzeb Mirza, Wei Lin, Jakub Micorek, Marc Masana, Mateusz Kozinski, Horst Possegger, Horst Bischof

We propose to store these affine parameters as a memory bank for each weather condition and plug-in their weather-specific parameters during driving (i. e. test time) when the respective weather conditions are encountered.

Autonomous Driving Incremental Learning +2

Instance Segmentation and Tracking with Cosine Embeddings and Recurrent Hourglass Networks

no code implementations6 Jun 2018 Christian Payer, Darko Štern, Thomas Neff, Horst Bischof, Martin Urschler

Furthermore, we train the network with a novel embedding loss based on cosine similarities, such that the network predicts unique embeddings for every instance throughout videos.

Instance Segmentation Segmentation +1

Deep 2.5D Vehicle Classification with Sparse SfM Depth Prior for Automated Toll Systems

no code implementations9 May 2018 Georg Waltner, Michael Maurer, Thomas Holzmann, Patrick Ruprecht, Michael Opitz, Horst Possegger, Friedrich Fraundorfer, Horst Bischof

Furthermore due to the design of the network, at test time only the 2D camera images are required for classification which enables the usage in portable computer vision systems.

3D Object Classification Classification +2

Prioritized Multi-View Stereo Depth Map Generation Using Confidence Prediction

no code implementations22 Mar 2018 Christian Mostegel, Friedrich Fraundorfer, Horst Bischof

In the second step, we rank the resulting view clusters (i. e. key views with matching partners) according to their impact on the fulfillment of desired quality parameters such as completeness, ground resolution and accuracy.

3D Reconstruction

Scalable Surface Reconstruction from Point Clouds with Extreme Scale and Density Diversity

no code implementations CVPR 2017 Christian Mostegel, Rudolf Prettenthaler, Friedrich Fraundorfer, Horst Bischof

In this paper we present a scalable approach for robustly computing a 3D surface mesh from multi-scale multi-view stereo point clouds that can handle extreme jumps of point density (in our experiments three orders of magnitude).

Surface Reconstruction

PetroSurf3D - A Dataset for high-resolution 3D Surface Segmentation

no code implementations6 Oct 2016 Georg Poier, Markus Seidl, Matthias Zeppelzauer, Christian Reinbacher, Martin Schaich, Giovanna Bellandi, Alberto Marretta, Horst Bischof

The development of powerful 3D scanning hardware and reconstruction algorithms has strongly promoted the generation of 3D surface reconstructions in different domains.

Interactive Segmentation Segmentation +1

Grid Loss: Detecting Occluded Faces

no code implementations1 Sep 2016 Michael Opitz, Georg Waltner, Georg Poier, Horst Possegger, Horst Bischof

Detection of partially occluded objects is a challenging computer vision problem.

Face Detection

ATGV-Net: Accurate Depth Super-Resolution

no code implementations27 Jul 2016 Gernot Riegler, Matthias Rüther, Horst Bischof

We demonstrate that it is feasible to train our method solely on synthetic data that we generate in large quantities for this task.

Depth Map Super-Resolution Image Super-Resolution +1

UAV-based Autonomous Image Acquisition with Multi-View Stereo Quality Assurance by Confidence Prediction

no code implementations6 May 2016 Christian Mostegel, Markus Rumpler, Friedrich Fraundorfer, Horst Bischof

In this paper we present an autonomous system for acquiring close-range high-resolution images that maximize the quality of a later-on 3D reconstruction with respect to coverage, ground resolution and 3D uncertainty.

3D Reconstruction

Using Self-Contradiction to Learn Confidence Measures in Stereo Vision

no code implementations CVPR 2016 Christian Mostegel, Markus Rumpler, Friedrich Fraundorfer, Horst Bischof

Learned confidence measures gain increasing importance for outlier removal and quality improvement in stereo vision.

Building with Drones: Accurate 3D Facade Reconstruction using MAVs

no code implementations25 Feb 2015 Shreyansh Daftry, Christof Hoppe, Horst Bischof

Automatic reconstruction of 3D models from images using multi-view Structure-from-Motion methods has been one of the most fruitful outcomes of computer vision.

3D Reconstruction

Indoor Activity Detection and Recognition for Sport Games Analysis

no code implementations25 Apr 2014 Georg Waltner, Thomas Mauthner, Horst Bischof

This paper describes recognition of single player activities in sport with special emphasis on volleyball.

Action Detection Activity Detection +1

Geometric Abstraction from Noisy Image-Based 3D Reconstructions

no code implementations19 Apr 2014 Thomas Holzmann, Christof Hoppe, Stefan Kluckner, Horst Bischof

Creating geometric abstracted models from image-based scene reconstructions is difficult due to noise and irregularities in the reconstructed model.

Revisiting loss-specific training of filter-based MRFs for image restoration

no code implementations16 Jan 2014 Yunjin Chen, Thomas Pock, René Ranftl, Horst Bischof

It is now well known that Markov random fields (MRFs) are particularly effective for modeling image priors in low-level vision.

Image Denoising Image Restoration

Learning $\ell_1$-based analysis and synthesis sparsity priors using bi-level optimization

no code implementations16 Jan 2014 Yunjin Chen, Thomas Pock, Horst Bischof

We then introduce an approach to learn both analysis operator and synthesis dictionary simultaneously by using a unified framework of bi-level optimization.

Dictionary Learning Image Denoising

Context-Sensitive Decision Forests for Object Detection

no code implementations NeurIPS 2012 Peter Kontschieder, Samuel R. Bulò, Antonio Criminisi, Pushmeet Kohli, Marcello Pelillo, Horst Bischof

In this paper we introduce Context-Sensitive Decision Forests - A new perspective to exploit contextual information in the popular decision forest framework for the object detection problem.

General Classification Object +4

Semantically Aware Urban 3D Reconstruction with Plane-Based Regularization

no code implementations ECCV 2018 Thomas Holzmann, Michael Maurer, Friedrich Fraundorfer, Horst Bischof

We propose a method for urban 3D reconstruction, which incorporates semantic information and plane priors within the reconstruction process in order to generate visually appealing 3D models.

3D Reconstruction

Alternating Decision Forests

no code implementations CVPR 2013 Samuel Schulter, Paul Wohlhart, Christian Leistner, Amir Saffari, Peter M. Roth, Horst Bischof

Contrary to Boosted Trees, in our method the loss minimization is an inherent part of the tree growing process, thus allowing to keep the benefits of common Random Forests, such as, parallel processing.

object-detection Object Detection

Diffusion Processes for Retrieval Revisited

no code implementations CVPR 2013 Michael Donoser, Horst Bischof

In this paper we revisit diffusion processes on affinity graphs for capturing the intrinsic manifold structure defined by pairwise affinity matrices.

Retrieval

Robust Real-Time Tracking of Multiple Objects by Volumetric Mass Densities

no code implementations CVPR 2013 Horst Possegger, Sabine Sternig, Thomas Mauthner, Peter M. Roth, Horst Bischof

Combining foreground images from multiple views by projecting them onto a common ground-plane has been recently applied within many multi-object tracking approaches.

3D Object Tracking Multi-Object Tracking

Optimizing 1-Nearest Prototype Classifiers

no code implementations CVPR 2013 Paul Wohlhart, Martin Kostinger, Michael Donoser, Peter M. Roth, Horst Bischof

The development of complex, powerful classifiers and their constant improvement have contributed much to the progress in many fields of computer vision.

Accurate Object Detection with Joint Classification-Regression Random Forests

no code implementations CVPR 2014 Samuel Schulter, Christian Leistner, Paul Wohlhart, Peter M. Roth, Horst Bischof

In this way, we can simultaneously predict the object probability of a window in a sliding window approach as well as regress its aspect ratio with a single model.

Classification General Classification +5

Occlusion Geodesics for Online Multi-Object Tracking

no code implementations CVPR 2014 Horst Possegger, Thomas Mauthner, Peter M. Roth, Horst Bischof

Robust multi-object tracking-by-detection requires the correct assignment of noisy detection results to object trajectories.

motion prediction Multi-Object Tracking +2

Event-Driven Stereo Matching for Real-Time 3D Panoramic Vision

no code implementations CVPR 2015 Stephan Schraml, Ahmed Nabil Belbachir, Horst Bischof

This paper presents a stereo matching approach for a novel multi-perspective panoramic stereo vision system, making use of asynchronous and non-simultaneous stereo imaging towards real-time 3D 360deg vision.

Stereo Matching Stereo Matching Hand

In Defense of Color-Based Model-Free Tracking

no code implementations CVPR 2015 Horst Possegger, Thomas Mauthner, Horst Bischof

We evaluate our approach on recent online tracking benchmark datasets demonstrating state-of-the-art results.

Object Object Tracking

Encoding Based Saliency Detection for Videos and Images

no code implementations CVPR 2015 Thomas Mauthner, Horst Possegger, Georg Waltner, Horst Bischof

We present a novel video saliency detection method to support human activity recognition and weakly supervised training of activity detection algorithms.

Activity Detection Human Activity Recognition +4

Variational Depth Superresolution Using Example-Based Edge Representations

no code implementations ICCV 2015 David Ferstl, Matthias Ruther, Horst Bischof

Both the sparse coding and the variational superresolution of the depth are solved based on a primal-dual formulation.

BIER - Boosting Independent Embeddings Robustly

no code implementations ICCV 2017 Michael Opitz, Georg Waltner, Horst Possegger, Horst Bischof

Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of large embeddings.

Image Retrieval Metric Learning +1

FuseSeg: LiDAR Point Cloud Segmentation Fusing Multi-Modal Data

no code implementations18 Dec 2019 Georg Krispel, Michael Opitz, Georg Waltner, Horst Possegger, Horst Bischof

We introduce a simple yet effective fusion method of LiDAR and RGB data to segment LiDAR point clouds.

Point Cloud Segmentation

FAST3D: Flow-Aware Self-Training for 3D Object Detectors

no code implementations18 Oct 2021 Christian Fruhwirth-Reisinger, Michael Opitz, Horst Possegger, Horst Bischof

In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors.

Autonomous Driving Object +1

3D Human Pose Estimation Using Möbius Graph Convolutional Networks

no code implementations20 Mar 2022 Niloofar Azizi, Horst Possegger, Emanuele Rodolà, Horst Bischof

In particular, this allows us to directly and explicitly encode the transformation between joints, resulting in a significantly more compact representation.

3D Human Pose Estimation

Sparse Message Passing Network with Feature Integration for Online Multiple Object Tracking

no code implementations6 Dec 2022 Bisheng Wang, Horst Possegger, Horst Bischof, Guo Cao

Existing Multiple Object Tracking (MOT) methods design complex architectures for better tracking performance.

Multiple Object Tracking

MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds

no code implementations14 Dec 2022 Georg Krispel, David Schinagl, Christian Fruhwirth-Reisinger, Horst Possegger, Horst Bischof

The sensing process of large-scale LiDAR point clouds inevitably causes large blind spots, i. e. regions not visible to the sensor.

3D Object Detection Autonomous Driving +4

Robust Localization of Key Fob Using Channel Impulse Response of Ultra Wide Band Sensors for Keyless Entry Systems

no code implementations16 Jan 2024 Abhiram Kolli, Filippo Casamassima, Horst Possegger, Horst Bischof

Using neural networks for localization of key fob within and surrounding a car as a security feature for keyless entry is fast emerging.

MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection

no code implementations21 Mar 2024 Jakub Micorek, Horst Possegger, Dominik Narnhofer, Horst Bischof, Mateusz Kozinski

We propose a novel approach to video anomaly detection: we treat feature vectors extracted from videos as realizations of a random variable with a fixed distribution and model this distribution with a neural network.

Anomaly Detection Denoising +2

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