S
Stefan Hinterstoisser
Researcher at Google
Publications - 33
Citations - 4077
Stefan Hinterstoisser is an academic researcher from Google. The author has contributed to research in topics: Object detection & Object (computer science). The author has an hindex of 23, co-authored 33 publications receiving 3249 citations. Previous affiliations of Stefan Hinterstoisser include Technische Universität München & Ludwig Maximilian University of Munich.
Papers
More filters
Book ChapterDOI
Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes
Stefan Hinterstoisser,Vincent Lepetit,Slobodan Ilic,Stefan Johannes Josef Holzer,Gary Bradski,Kurt Konolige,Nassir Navab +6 more
TL;DR: A framework for automatic modeling, detection, and tracking of 3D objects with a Kinect and shows how to build the templates automatically from 3D models, and how to estimate the 6 degrees-of-freedom pose accurately and in real-time.
Proceedings ArticleDOI
Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes
Stefan Hinterstoisser,Stefan Johannes Josef Holzer,Cedric Cagniart,Slobodan Ilic,Kurt Konolige,Nassir Navab,Vincent Lepetit +6 more
TL;DR: This work presents a method for detecting 3D objects using multi-modalities based on an efficient representation of templates that capture the different modalities, and shows in many experiments on commodity hardware that it significantly outperforms state-of-the-art methods on single modalities.
Journal ArticleDOI
Gradient Response Maps for Real-Time Detection of Textureless Objects
Stefan Hinterstoisser,Cedric Cagniart,Slobodan Ilic,Peter Sturm,Nassir Navab,Pascal Fua,Vincent Lepetit +6 more
TL;DR: A method for real-time 3D object instance detection that does not require a time-consuming training stage, and can handle untextured objects, and is much faster and more robust with respect to background clutter than current state-of-the-art methods is presented.
Proceedings ArticleDOI
Dominant orientation templates for real-time detection of texture-less objects
TL;DR: This work presents a method for real-time 3D object detection that does not require a time consuming training stage, and can handle untextured objects, and is a novel template representation that is designed to be robust to small image transformations.
Book ChapterDOI
On Pre-trained Image Features and Synthetic Images for Deep Learning
TL;DR: A simple trick is shown that is sufficient to train very effectively modern object detectors with synthetic images only: freeze the layers responsible for feature extraction to generic layers pre-trained on real images, and train only the remaining layers with plain OpenGL rendering.