Torsten Sattler

Associate Professor at Imaging and Image Analysis

Torsten Sattler is an associate professor in the research group Computer vision and medical image analysis. His main research interests focus around developing robust and reliable 3D computer vision algorithms for applications such as Mixed Reality, Self-Driving Cars, and Robotics. To this end, Torsten works on integrating higher-level scene understanding into techniques such as visual localization and mapping. He is further interested in real-time computer vision algorithms and machine learning for computer vision tasks.

Source: chalmers.se

Showing 11 publications

2019

Understanding the Limitations of CNN-based Absolute Camera Pose Regression

Torsten Sattler, Qunjie Zhou, Marc Pollefeys et al
Paper in proceedings
2019

Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System

Lionel Heng, Benjamin Choi, Zhaopeng Cui et al
2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), p. 4695-4702
Paper in proceedings
2019

Efficient 2D-3D Matching for Multi-Camera Visual Localization

Marcel Geppert, Peidong Liu, Zhaopeng Cui et al
2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), p. 5972-5978
Paper in proceedings
2019

SurfelMeshing: Online Surfel-Based Mesh Reconstruction

Thomas Schops, Torsten Sattler, Marc Pollefeys
IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. In Press
Journal article
2019

A cross-season correspondence dataset for robust semantic segmentation

Måns Larsson, Erik Stenborg, Lars Hammarstrand et al
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 2019-June, p. 9524-9534
Paper in proceedings
2019

Night-to-day image translation for retrieval-based localization

Asha Anoosheh, Torsten Sattler, Radu Timofte et al
Proceedings - IEEE International Conference on Robotics and Automation. Vol. 2019-May, p. 5958-5964
Paper in proceedings
2019

Hybrid scene Compression for Visual Localization

Federico Camposeco, Andrea Cohen, Marc Pollefeys et al
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), p. 7645-7654
Paper in proceedings
2019

Bad slam: Bundle adjusted direct RGB-D slam

Thomas Schops, Torsten Sattler, Marc Pollefeys
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 2019-June, p. 134-144
Paper in proceedings
2019

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

Mihai Dusmanu, Ignacio Rocco, Tomas Pajdla et al
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), p. 8084-8093
Paper in proceedings
2019

Real-Time Dense Mapping for Self-Driving Vehicles using Fisheye Cameras

Zhaopeng Cui, Lionel Heng, Ye Chuan Yeo et al
2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), p. 6087-6093
Paper in proceedings
2019

Incremental visual-inertial 3d mesh generation with structural regularities

Antoni Rosinol, Torsten Sattler, Marc Pollefeys et al
Proceedings - IEEE International Conference on Robotics and Automation. Vol. 2019-May, p. 8220-8226
Paper in proceedings

Save references

If you have installed Zotero or Mendeley on your computer you can use a plugin to extract references from the publications you see.

Download plugins:
Zotero
Mendeley

There are no projects.
There might be more projects where Torsten Sattler participates, but you have to be logged in as a Chalmers employee to see them.