Hayko Riemenschneider

Hayko Riemenschneider is currently a post-doctoral researcher under Prof. Luc Van Gool at the Computer Vision Laboratory at ETH Zurich.
He received a Doctor of Philosophy (PhD) in computer science in 2012, a Master of Science (MSc) in 2008 and a
Bachelor of Science (BSc) in 2006 from the Graz University of Technology, Austria.

He is team and project leading for the ERC project VarCity where the interest lies in large-scale urban modelling.
The goal is to reconstruct and augment cities with semantic and dynamic aspects, and have fun while doing so!

Quicklinks: Yet Another Computer Vision Index To Datasets (YACVID) - 3D Semantic Segmentation Challenge

Hayko Riemenschneider looking...!
As all in life, this site will grow and enrich itself with time.
Contact:
Institut fuer Bildverarbeitung
Sternwartstrasse 7
ETH-Zentrum
CH - 8092 Zurich, Schweiz
Tel: +41 44 63 20258
Fax: +41 44 63 21199
Buro: ETF C114
E-mail: hayko (at) vision (dot) ee (dot) ethz (dot) ch

Research Topics

Shape-based detection / matching via Semantic Object Detection/Segmentation to 3D Multiview Semantization

Procedural Cities - 3D Semantic Segmentation Challenge

Efficient 3D Surface Reconstruction

Next Best View Planning, Multi-view Summary and Clustering to Navigation

  • Semantic Urban environment reconstruction and modeling
    1. City-scale 3D point cloud processing, recognition and segmentation
    2. Dense 3D surface modelling (piecewise planar, mesh, procedural, and hybrids)
    3. Joint object detection and segmentation
    4. Multi-structure fitting
    5. Symmetry and repetition analysis
    6. Procedural modeling of architecture
  • Semantic Detection, Classification and Segmentation
    1. Joint object detection and segmentation
    2. Perspective detection
    3. Semantic Scene Understanding
  • Shape representation and matching
    1. Shape-based object detection
    2. Extraction of stable contour edges from images
    3. Partial Contours for Efficient Matching (PACEM)
    4. Repeatable segmentation through shape matching
    5. Sketch-based image internet search
  • Figure/ground segmentation/classification for patches, objects and motions
    1. Verification through segmentation
    2. Descriptors for noisy patches
    3. Action segmentation by motion analysis
  • Online learning and recognition from tracking

Projects

  • VarCity for semantic and dynamic city modeling (team leader, project management, and researcher)
  • CityFit for high-quality city reconstructions (main vision researcher, developer)
  • SSLdoc for large scale graph clustering (main researcher, developer)
  • NHM for recognition of butterfly species (supervision and researcher)
  • IMPEx for retrieval of patent documents (retrieval researcher, developer)
  • EVOLARIS for object, CD cover and billboard matching and retrieval (main vision researcher, developer)

Supervision (Phds)

Datasets

  • Database search and collaborative editing yacvid
  • ETHZ CVL VarCity 3D Challenge leadership board - procedural semantic challenge
  • ETHZ CVL RueMonge 2014 yacvid#251 - 700m dense pcl/pix/mesh semantic annotation
  • ETHZ CVL SumMe yacvid#245 - video summary annotations
  • ETHZ CVL Synthesizability project - texture synthesis annotation
  • ETHZ CVL Fraumunster project - manual collection of fraumunster
  • ETHZ CVL Webcam Interestingness yacvid#321 - 159 webcam streams with interestingness rating
  • ETHZ CVL ECP 2011 soon - updated hausmann facade annotation
  • ICG Graz240 yacvid#86 - 240 architectural styles
  • ICG / TUD Crossing yacvid#9 - dense pixelwise person annotation
  • ICG / ETHZ Shapes link - dense pixewisel annotation of ETHZ shapes

Recent Publications

Click here for a complete list of publication.
2016

  • Architectural Decomposition for 3D Landmark Building Understanding, WACV 2016, Lake Placid, New York. (PDF, project)
    N. Kobyshev, H. Riemenschneider, A. Bodis-Szomoru, L. Van Gool
  • Mobile Phone and Cloud - a Dream Team for 3D Reconstruction , WACV 2016, Lake Placid, New York. (PDF, project)
    A. Locher, M. Perdoch, H. Riemenschneider, L. Van Gool
2015
  • Superpixel Meshes for Fast Edge-Preserving Surface Reconstruction CVPR 2015, Boston, Massachusetts. (PDF, poster, project)
    A. Bodis-Szomoru, H. Riemenschneider, L. Van Gool
  • 3D All The Way: Semantic Segmentation of Urban Scenes from Start to End in 3D CVPR 2015, Boston, Massachusetts. (PDF, poster, project)
    A. Martinovic, J. Knopp, H. Riemenschneider, L. Van Gool
  • What is needed for Multi-View Semantic Segmentation? CVPR 2015 Workshop on Semantics for Visual SLAM, Boston, Massachusetts. (pdf, poster, project)
    H. Riemenschneider, A. Bodis-Szomoru, A. Martinovic, J. Weissenberg, L. Van Gool
  • Mapping for Autonomous Vehicles and Probes Workgroup Vision for Autonomous Vehicles and Probes Report, Dagstuhl, Germany. (PDF, poster, project)
    Y. Furukawa, A. Gasteratos, M. Havlena, H. Riemenschneider, T. Sattler, A. Torii, V. Usenko, Edited by A. Bruhn, A. Imiya, A. Leonardis, T. Pajdla
2014
  • Navigation using Special Buildings as Signposts MapInteract 2014 , Dallas, Texas (PDF, supplemental material)
    J. Weissenberg, M. Gygli, H. Riemenschneider, L. Van Gool
  • Matching Features Correctly through Semantic Understanding 3DV 2014, Tokyo, Japan (PDF, project)
    N. Kobyshev, H. Riemenschneider, L. Van Gool
  • An Integer Linear Programming model for View Selection on Overlapping Camera Clusters 3DV 2014, Tokyo, Japan (PDF, project)
    M. Mauro, H. Riemenschneider, L. Van Gool, A. Signoroni, R. Leonardi
  • Learning Where To Classify In Multi-View Semantic Segmentation ECCV 2014, Zurich, Switzerland. (PDF, project)
    H. Riemenschneider, A. Bodis-Szomoru, J. Weissenberg, L. Van Gool
  • Creating Summaries from User Videos ECCV 2014, Zurich, Switzerland. (PDF, project+dataset)
    M. Gygli, H. Grabner, H. Riemenschneider, L. Van Gool
  • Frankenhorse: Automatic Completion of Articulating Objects from Image-based Reconstruction BMVC 2014, Nottingham, UK. (PDF, AbstractPage, project)
    A. Mansfield, N. Kobyshev, H. Riemenschneider, W. Chang, L. Van Gool
  • A unified framework for content-aware view selection and planning through view importance BMVC 2014, Nottingham, UK. (PDF, AbstractPage, project)
    M. Mauro, H. Riemenschneider, L. Van Gool, A. Signoroni, R. Leonardi
  • Fast, Approximate Piecewise-Planar Modeling Based on Sparse Structure-from-Motion and Dense Superpixels CVPR 2014, Columbus, Ohio. (PDF, poster, video)
    A. Bodis-Szomoru, H. Riemenschneider, L. Van Gool
  • The Synthesizability of texture examples CVPR 2014, Columbus, Ohio. (PDF, project+code)
    D. Dai, H. Riemenschneider, L. Van Gool
2013
  • Example-based Facade Texture Synthesis ICCV 2013, Sydney, Australia. (PDF, project)
    D. Dai, H. Riemenschneider, L. Van Gool
  • The Interestingness of Images ICCV 2013, Sydney, Australia. (PDF, project)
    M. Gygli, H. Grabner, H. Riemenschneider, F. Nater, L. Van Gool
  • Hierarchical Segment Support for Categorical Image Labeling ICCVW 2013, Sydney, Australia. (PDF)
    M Donoser, H Riemenschneider
  • Overlapping camera clustering through dominant sets for scalable 3D reconstruction BMVC 2013, Bristol, UK. (PDF, AbstractPage, project)
    M. Mauro, H. Riemenschneider, L. Van Gool, R. Leonardi
  • Is there a Procedural Logic to Architecture? CVPR 2013, Portland, USA. (PDF, Poster, project)
    J. Weissenberg, H. Riemenschneider, M. Prasad, L. Van Gool.
2012
  • Hough Regions for Joining Instance Localization and Segmentation. ECCV 2012, Florence, Italy. (PDF, TUD-crossing annotation, project)
    H. Riemenschneider, S. Sternig. M. Donoser, P. Roth and H. Bischof.
  • Irregular lattices for complex shape grammar facade parsing. CVPR 2012, Providence, USA. (PDF, ICG Graz50, project)
    H. Riemenschneider, U. Krispel, W. Thaller, M. Donoser, S. Havemann, D. Fellner, H. Bischof.
  • Object detection by partial shape matching, category models and joint segmentation. PhD Thesis 2012
    H. Riemenschneider under supervision of Dr. M. Donoser and Prof. H. Bischof, Institute for Computer Graphics and Vision, TU Graz, Austria. (PDF)
2011
  • Discriminative Learning of Contour Fragments for Object Detection. In BMVC 2011, Dundee, UK. (PDF, AbstractPage)
    P. Kontschieder, H. Riemenschneider, M. Donoser, H. Bischof.
  • Highly Consistent Sequential Segmentation. In SCIA 2011, Sweden. (PDF)
    M. Donoser, M. Urschler, H. Riemenschneider, H. Bischof.
  • IS-Match: Partial Shape Matching by Efficiently Solving an Order Preserving Assignment Problem. IPSJ 2011 (PDF)
    M. Donoser, H. Riemenschneider and H. Bischof.
  • Image retrieval by shape-focused sketching of objects. In CVWW 2011, Austria. (PDF)
    H. Riemenschneider, M. Donoser and H. Bischof.
2010
  • Using Partial Edge Contour Matches for Efficient Object Category Localization. In ECCV 2010, Crete, Greece. (PDF, data)
    H. Riemenschneider, M. Donoser and H. Bischof.
  • Shape prototype signatures for action recognition. ICPR 2010, Istanbul, Turkey. (PDF)
    M. Donoser, H. Riemenschneider and H. Bischof.
  • Shape guided Maximally Stable Extremal Region (MSER) tracking. ICPR 2010, Istanbul, Turkey. (PDF)
    M. Donoser, H. Riemenschneider and H. Bischof.
  • Linked Edges as Stable Region Boundaries. CVPR 2010, San Francisco, USA. (PDF, data)
    M. Donoser, H. Riemenschneider and H. Bischof.
  • Robust Object Detection by Classifier Cubes and Local Verification. In AAPR 2010, Austria. (PDF)
    S. Sternig, H. Riemenschneider, P. Roth, M. Donoser, H. Bischof.
2009
  • Efficient Partial Shape Matching of Outer Contours. ACCV 2009, Xian, China. (PDF)
    M. Donoser, H. Riemenschneider and H. Bischof.
  • Bag of Optical Flow Volumes for Image Sequence Recognition. BMVC 2009, London, UK. (PDF, AbstractPage)
    H. Riemenschneider, M. Donoser and H. Bischof.
  • Finding Stable Extremal Region Boundaries. AAPR 2009, Stainz, Austria. (PDF) Best Paper Award
    H. Riemenschneider, M. Donoser and H. Bischof.
2008
  • Online Object Recognition by MSER Trajectories. ICPR 2008, Tampa, USA. (PDF)
    H. Riemenschneider, M. Donoser and H. Bischof.
  • Robust Online Object Learning and Recognition by MSER Tracking. In CVWW 2008, Austria. (PDF)
    H. Riemenschneider, M. Donoser and H. Bischof.
  • Online Object Recognition using MSER Tracking. Master Thesis 2008
    H. Riemenschneider under supervision of Dr. M. Donoser and Prof. H. Bischof, Institute for Computer Graphics and Vision, TU Graz, Austria. (PDF)

Academic services and talks

  • Reviewer for CVPR, ICCV, ECCV, BMVC, ACCV, AAPR, ISPRS, UIST, IMAVIS, SPL, MFS, PCV, TOG, TVCG, JAIDM
  • Demo and public relations chair at CVL.
  • Project organizer for the European Research Council project VarCity.
  • Talk and presentation at IMAGINE research group, France.
  • Talk and presentation at Semantics for Visual Reconstruction and SLAM, Boston, USA.
  • Talk and presentation at University of Bonn, Germany.
  • Talk and presentation at Architecture meets Vision meets Architecture meeting, Switzerland.














Quicklinks

YACVID online!
Yet Another Computer Vision Index To Datasets (YACVID)

Varcity 3D Challenge online!
The VarCity 3D Semantic Segmentation Challenge based on our ECCV 2014 paper is now online for data and evaluation code!

Varcity Videos!
The VarCity Video Collection based on our previous papers is online!

Publications
Google Scholar DBLP Linkedin

News

December, 9th 2015: OpenLabNight!
The VarCity projects including the first full city game fly-over are shown during the OpenLabNight @ Computer Vision Lab, ETH Zurich!

Nov, 8th 2015: 3D Cities for Autonomous Cars?
VarCity was discussed during the Dagstuhl Seminar for Vision for Autonomous Vehicles and Probes at Schloss Dagstuhl, Germany.

Oct, 22nd 2015: Papers at WACV 2016 accepted!
Two papers were accepted at Winter Conference on Applications of Computer Vision (WACV) 2016, Lake Placid, USA.

Sep, 21th 2015: Showcase!
VarCity was showcased by the ERC Funding Agency.

June, 30th 2015: Presentation!
Presentation and discussion at a PhD examination at IMAGINE research group at the Universite Paris Est, Paris, France.

June, 11th 2015: Presentation!
Presentation at the Workshop for Semantics for Visual Reconstruction and SLAM at CVPR 2015, Boston.

May, 11th 2015: Project Meeting!
Varcity project and collaborators meeting was held jointly with the CVL Workshop at Schloss Rapperswil, Switzerland and special guest star
Richard Hartley!

March, 19th 2015: Presentation!
Presentation at University of Bonn, Germany.

March, 11th 2015: YACVID for 2 years now!
+250 datasets and 17400 visitors in two years on the Yet Another Computer Vision Index To Datasets (YACVID) website!

March, 2nd 2015: Papers at CVPR 2015 accepted!
Two papers were accepted at Computer Vision and Pattern Recognition (CVPR) 2015, Boston.

December, 3rd 2014: Demo Visit!
Demonstration exchange with Davide Scaramuzza, Robotics and Perception Group, University Zurich.

December, 2rd 2014: Project Meeting!
Project and collaborators meeting is on at Villa Hatt, Zurich!

October, 1st 2014: 3D Challenge online!
The VarCity 3D Semantic Segmentation Challenge based on our ECCV 2014 paper is now online for data and evaluation code!

September, 12th 2014: PhD Defense!
Dr. Julien Weisseberg has finished his PhD!

September, 8th 2014: Papers at 3DV 2014 accepted!
Two papers were accepted at 3DV 2014, Tokyo.

September, 5th 2014: Conference in town!
The ECCV 2014 will be held in our town this year!

August, 28th 2014: Project Meeting!
Project and collaborators meeting will be held!

July, 8th 2014: Papers at BMVC 2014 accepted!
Two papers were accepted at BMVC 2014, Nottingham. Looking forward to the Star Wars dinner. :)

June, 15th 2014: Papers at ECCV 2014 accepted!
Two papers were accepted at ECCV 2014, Zurich.

April, 3rd 2014: Project Meeting
Yet another full varcity projecting successfully held a secret special location, Zurich.

February, 24th 2014: Papers at CVPR 2014 accepted!
Two papers were accepted at Computer Vision and Pattern Recognition (CVPR) 2014, Columbus, Ohio.

January, 31th 2014: PhD Defense!
Dr. Alex Mansfield has finished his PhD!

September, 3rd 2013: Project Meeting!
Project and collaborators meeting is on at St. Peter Church, Zurich!

August, 29th 2013: Papers at ICCV 2013 accepted!
Two papers were accepted at International Conference on Computer Vision (ICCV) 2013, Sydney, Australia.

August, 15th 2013: Architecture meets Vision meets Architecture Meeting!
Interactions between architecture and computer vision workshop was held at CVL Seminar, ETH Zurich!

July, 1st 2013: Paper at BMVC 2013 accepted!
Our work on view clustering for reconstructions was accepted at British Machine Vision Conference (BMVC) 2013, Bristol, UK.

May, 15th 2013: Swiss Vision Day!
The VarCity project and its publications are shown at the Swiss Vision Day @ ETH Zurich! Lots of posters, demos, food, and fun. Join us again next year!

May, 8th 2013: Project meeting!
Project and collaborators meeting is on today at main campus, ETH Zurich!

March, 11th 2013: YACVID revisited!
Yet Another Computer Vision Index To Datasets (YACVID) is online!

February, 25th 2013: Paper at CVPR 2013 accepted!
Our work on procedural grammar learning was accepted at Computer Vision and Pattern Recognition (CVPR), Portland, Oregon.

January, 18th 2013: Project meeting!
Project and collaborators meeting is on today at Villa Hatt, ETH Zurich!

December, 19th 2012: OpenLabDay!
The VarCity projects are shown at the OpenLabDay @ Computer Vision Lab, ETH Zurich! Lots of demos, food, and fun. Join us again next time!

September, 14th 2012: Project meeting!
Project and collaborators meeting went on today at HIT ValueLab, Hoenggerberg! The
ValueLab is an environment for collaborative design and management.

September, 1st 2012: Website online!
First version of the VarCity project website is online! More (re)construction soon!

August, 15th 2012: Kickoff meeting!
Kickoff meeting for all partners and people involved went on today at the Zurich Zoo!

June, 25th 2012: Paper at ECCV 2012 accepted!
Our work on joining object localization and segmentation was accepted at the European Conference on Computer Vision (ECCV), Florence.

March, 2nd 2012: Paper at CVPR 2012 accepted!
Our work on irregular lattices for complex architecture parsing was accepted at the Conference on Computer Vision and Pattern Recognition (CVPR), New York.

June, 28th 2011: Paper at BMVC 2011 accepted!
Our work on discriminative learning of contour fragments was accepted at the British Machine Vision Conference (BMVC), United Kingdom.

March, 3rd 2011: Paper at SCIA 2011 accepted!
Our work on highly consistent and repeatable segmentations was accepted at the Scandinavian Conference on Image Analysis (SCIA), Sweden.

October, 15th 2010: PACEM descriptor
A page for the PArtial Contours for Efficient Matching (PACEM) descriptor used in our ECCV'2010 paper is now available.

June, 6th 2010: Paper at ECCV 2010 accepted!
Our paper "Using Partial Edge Contour Matches for Efficient Object Category Localization" by Hayko Riemenschneider, Michael Donoser and Horst Bischof was accepted to the European Conference on Computer Vision (ECCV) 2010 in Crete, Greece.

March, 31th 2010: Paper at CVPR 2010 accepted!
Our paper "Linked Edges as Stable Region Boundaries" from M. Donoser, H. Riemenschneider and H. Bischof was accepted for the Conference on Computer Vision and Pattern Recognition (CVPR) in San Francisco. The work looks at shape consistent regions leading to linked stable edges.

July, 16th 2009: Paper at ACCV 2009 accepted!
Our paper "Efficient Partial Shape Matching of Outer Contours" from M. Donoser, H. Riemenschneider and H. Bischof was accepted for the Asian Conference on Computer Vision (ACCV 2009) in Xian, China.

June, 22th 2009: Paper at BMVC 2009 accepted!
Our paper "Bag of Optical Flow Volumes for Image Sequence Recognition" accepted for British Machine Vision Conference (BMVC 2008) in London, United Kingdom.

May, 14th 2009: Best Scientific Paper Award at OAGM 2009
Our paper "Finding Stable Extremal Region Boundaries" from Hayko Riemenschneider, Michael Donoser, and Horst Bischof was awarded with the Best Scientific Paper Award at the Workshop of the Austrian Association for Pattern Recognition.

April, 1st 2009: Poster Presentation at ICVSS 2009
Our project "CITYFIT - High-quality urban reconstructions" was presented at the International Computer Vision Summer School (ICVSS 2009) in Sicily, Italy.

March, 30th 2009: Virtual Habitat Website online!
Virtual Habitat is a work group at the Institute for Computer Graphics and Vision at Graz University of Technology. The group has its focus on scientific research in the computer vision fields of object recognition and 3D modeling from digital images.

December, 8th 2008: Poster Presentation at ICPR 2008
Our paper "Online Object Recognition by MSER Trajectories" presented at the International Conference on Pattern Recognition (ICPR 2008) in Tampa Bay, Florida.
Locations of visitors to this page

This page has been edited by Hayko Riemenschneider