Conference Program

The color coding is as follows: All plenary talks will be held in Aula 2. The main venue for GCPR and the workshop is AH V. For VMV and the tutorial the events will take place in AH VI. All venues are presented on a dedicated page.

Note: All dates are available as icalendar file.

Instructions for presenting (oral talk and poster) are available.

Conference Program Booklet

NC2 Workshop Program

Time Wed, 07.10. Thu, 08.10. Fri, 09.10. Sat, 10.10.
9:00 Keynote: Max Welling Keynote: Andrew Blake Part Ia:
Causal Language
Oral Sessions
10:00 Plenary Oral Session 1 Plenary Oral Session 2
10:30 CoffeeCoffee
10:45 CoffeeCoffee CoffeeCoffee
11:00 Part Ib:
Causal Reasoning
Poster Session
11:15 Oral Session 3
Math. Foundations & Image Processing
Oral Session 3
Oral Session 6
Recognition & Scene Understanding
Oral Session 6
Invited Talk: Joschka Boedecker
12:30 LunchLunch LunchLunch LunchLunch (Restaurant Lara)
Menu (German, 2.5MB)
13:00 Opening
13:15 Keynote: Niloy Mitra
13:30 Oral Session 4
Biomedical Image Analysis and Applications
Oral Session 4
Images andVideo
Poster Session 2 Part II:
Causal Discovery
Oral Sessions
14:15 CoffeeCoffee
14:45 GCPR Opening Oral Session 1
15:00 German Pattern Recognition Award Talk CoffeeCoffee CoffeeCoffee CoffeeCoffee
15:30 Poster Session 1 Closing & Awards Part III:
Poster Session
16:00 CoffeeCoffee Invited Talk: Christian Igel
16:15 Oral Session 2
Motion and Reconstruction
Oral Session 2
17:00 Oral Session 5
Human Pose Analysis
Oral Session 5
17:15 Meeting of the GI Fachgruppe Neural Networks
18:00 DAGM Meeting
19:00 Conference DinnerConference Dinner

GCPR Oral Sessions

  • O2, Wed, 07.10. 16:15-17:45 (Motion and Reconstruction), AH V, Session Chair: Ullrich Koethe

    • Road Condition Estimation based on Spatio-Temporal Reflection Models

      Manuel Amthor, Bernd Hartmann, and Joachim Denzler

    • Discrete Optimization for Optical Flow

      Moritz Menze, Christian Heipke, and Andreas Geiger

    • Multi-Camera Structure from Motion with Eye-to-Eye Calibration

      Sandro Esquivel and Reinhard Koch

    • Estimating Vehicle Ego-Motion and Piecewise Planar Scene Structure from Optical Flow in a Continuous Framework

      Andreas Neufeld, Johannes Berger, Florian Becker, Frank Lenzen, and Christoph Schnörr

  • PO1, Thu, 08.10. 10:00-10:45 (Plenary Oral Session 1), Aula 2, Session Chair: Helmut Hayer

    • Point-wise Map Recovery and Refinement from Functional Correspondence

      Emanuele Rodola, Michael Moeller, Daniel Cremers (VMV)

    • Efficient Two-View Geometry Classification

      Johannes L. Schönberger, Alexander C. Berg, and Jan-Michael Frahm (GCPR)

  • O3, Thu, 08.10. 11:15-12:30 (Mathematical Foundations and Image Processing), AH V, Session Chair: Stefan Roth

    • A Convex Relaxation Approach to the Affine Subspace Clustering Problem

      Francesco Silvestri, Gerhard Reinelt, and Christoph Schnörr

    • Introducing Maximal Anisotropy into Second Order Coupling Models

      David Hafner, Christopher Schroers, and Joachim Weickert

    • Binarization Driven Blind Deconvolution for Document Image Restoration

      Thomas Köhler, Andreas Maier, and Vincent Christlein

  • O4, Thu, 08.10. 13:30-15:00 (Biometical Image Analysis and Applications), AH V, Session Chair: Simone Frintrop

    • Unsupervised and Accurate Extraction of Primitive Unit Cells from Crystal Images

      Niklas Mevenkamp and Benjamin Berkels

    • Copula Archetypal Analysis

      Dinu Kaufmann, Sebastian Keller, and Volker Roth

    • Interactive Image Retrieval for Biodiversity Research

      Alexander Freytag, Alena Schadt, and Joachim Denzler

    • Temporal Acoustic Words for Online Acoustic Event Detection

      Rene Grzeszick, Axel Plinge, and Gernot A. Fink

  • O5, Thu, 08.10. 17:00-17:45 (Human Pose Analysis), AH V, Session Chair: Angela Yao

    • Biternion Nets: Continuous Head Pose Regression from Discrete Training Labels

      Lucas Beyer, Alexander Hermans, and Bastian Leibe

    • A physics-based statistical model for human gait analysis

      Petrissa Zell and Bodo Rosenhahn

  • PO2, Fri, 09.10. 10:00-10:45 (Plenary Oral Session 2), Aula 2, Session Chair: Carsten Rother

    • Joint 3D Object and Layout Inference from a single RGB-D Image

      Andreas Geiger and Chaohui Wang (GCPR)

    • Variational Separation of Light Field Layers

      Ole Johannsen, Antonin Sulc, Bastian Goldlücke (VMV)

  • O6, Fri, 09.10. 11:15-12:30 (Recognition and Scene Understanding), AH V, Session Chair: Andreas Geiger

    • Object Proposals Estimation in Single Depth Images Using Compact 3D Shape Manifolds

      Shuai Zheng, Victor Adrian Prisacariu, Melinos Averkiou, Ming-Ming Cheng, Niloy J. Mitra, Jamie Shotton, Philip H.S. Torr, and Carsten Rother

    • The Long-Short Story of Movie Description

      Anna Rohrbach, Marcus Rohrbach, and Bernt Schiele

    • Graph-Based Deformable 3D Object Matching

      Bertram Drost and Slobodan Ilic


VMV Oral Sessions

  • O1, Wed, 07.10. 14:45-16:00 (Geometry), AH VI, Session Chair: Christian Rössl

    • Anisotropic Template Fitting for High Resolution Face Reconstruction

      Jascha Achenbach, Eduard Zell, Mario Botsch

    • Data Driven 3D Face Tracking Based on a Facial Deformation Model

      Dominik Sibbing, Leif Kobbelt

    • Simple, robust, constant-time bounds on-surface geodesic distances using point landmarks

      Oliver Burghard, Reinhard Klein

  • O2, Wed, 07.10. 16:15-17:45 (Visualization), AH VI, Session Chair: Holger Theisel

    • Temporal Coherence Predictor for Time Varying Volume Data Based on Perceptual Functions

      Tom Noonan, Lazaro Campoalegre, John Dingliana

    • Hierarchical Hashing for Pattern Search in 3D Vector Fields

      Zhongjie Wang, Hans-Peter Seidel, Tino Weinkauf

    • Interactive GPU-based Visualization of Scalar Data with Gaussian Distributed Uncertainty

      Steven Schlegel, Mathias Goldau, Gerik Scheuermann

    • A Taxonomy of Integration Techniques for Spatial and Non-Spatial Visualizations

      Johannes Sorger, Thomas Ortner, Harald Piringer, Gerd Hesina, Eduard Gröller, Eduard

  • PO1, Thu, 08.10. 10:00-10:45 (Plenary Oral Session 1), Aula 2, Session Chair: Helmut Hayer

    • Point-wise Map Recovery and Refinement from Functional Correspondence

      Emanuele Rodola, Michael Moeller, Daniel Cremers (VMV)

    • Efficient Two-View Geometry Classification

      Johannes L. Schönberger, Alexander C. Berg, and Jan-Michael Frahm (GCPR)

  • O3, Thu, 08.10. 11:15-12:30 (Rendering), AH VI, Session Chair: Michael Guthe

    • Vector-to-Closest-Point Octree for Surface Ray-Casting

      Ismail Demir, Rüdiger Westermann

    • Level-of-Detail for Production-Scale Path Tracing

      Magdalena Prus, Christian Eisenacher, Marc Stamminger

    • The Bounced Z-buffer for Indirect Visibility

      Oliver Nalbach, Tobias Ritschel, Hans-Peter Seidel

  • O4, Thu, 08.10. 13:30-15:00 (Images and Video), AH VI, Session Chair: Bastian Goldlücke

    • A Convex Clustering-based Regularizer for Image Segmentation

      Benjamin Hell, Markus Magnor

    • Temporally Consistent Wide Baseline Facial Performance Capture via Image Warping

      Markus Kettern, Anna Hilsmann, Peter Eisert

    • Efficient GPU Based Sampling for Scene-Space Video Processing

      Felix Klose, Oliver Wang, Jean-Charles Bazin, Markus Magnor, Alexander Sorkine-Hornung

    • Rotoscoping on Stereoscopic Images and Videos

      Dennis Bukenberger, Katharina Schwarz, Fabian Groh,Hendrik Lensch

  • O5, Thu, 08.10. 17:00-17:45 (Simulation), AH VI, Session Chair: Jan Bender

    • Tongue S(t)imulator - A Comprehensive Parametrized Pose Model for Speech Therapy

      Laura Haraké, Dorota Beltkiewicz, Gerrit Lochmann

    • Simulation of Water Condensation based on a Thermodynamic Approach using Implicit Surfaces

      Sebastian-Torsten Tillmann, Christian-Arved Bohn

  • PO2, Fri, 09.10. 10:00-10:45 (Plenary Oral Session 2), Aula 2, Session Chair: Carsten Rother

    • Joint 3D Object and Layout Inference from a single RGB-D Image

      Andreas Geiger and Chaohui Wang (GCPR)

    • Variational Separation of Light Field Layers

      Ole Johannsen, Antonin Sulc, Bastian Goldlücke (VMV)

  • O6. Fri, 09.10. 11:15-12:30 (Acquisition), AH VI, Session Chair: Martin Fuchs

    • Extrapolating Large-Scale Material BTFs under Cross-Device Constraints

      Heinz Christian Steinhausen, Dennis den Brok, Matthias Hullin, Reinhard Klein

    • Fast multiplexed acquisition of material reflectance

      Dennis den Brok, Heinz-Christian Steinhausen, Reinhard Klein

    • Light Field Imaging through Household Optics

      Alexander Wender, Julian Iseringhausen, Bastian Goldlücke, Martin Fuchs, Matthias Hullin


Poster Sessions

  • P1 Thu, 08.10. 15:00-17:00 (Poster Session 1)

    • 1

      Line3D: Efficient 3D Scene Abstraction for the Built Environment

      Manuel Hofer, Michael Maurer, and Horst Bischof

    • 2

      An Efficient Linearisation Approach for Variational Perspective Shape From Shading

      Daniel Maurer, Yong Chul Ju, Michael Breuß, and Andrés Bruhn

    • 3

      TomoGC: Binary Tomography by Constrained GraphCuts

      Jörg Hendrik Kappes, Stefania Petra, Christoph Schnörr, and Matthias Zisler

    • 4

      An Improved Eikonal Method for Surface Normal Integration

      Martin Baehr and Michael Breuß

    • 5

      Fast Techniques for Monocular Visual Odometry

      M. Hossein Mirabdollah and Bärbel Mertsching

    • 6

      Iterative Automated Foreground Segmentation in Video Sequences Using Graph Cuts

      Tomislav Hrkać and Karla Brkić

    • 7

      A Parametric Spectral Model for Texture-Based Salience

      Kasim Terzić, Sai Krishna, and J.M.H. du Buf

    • 8

      High Speed Lossless Image Compression

      Hendrik Siedelmann, Alexander Wender, and Martin Fuchs

    • 9

      Learning Reaction-Diffusion Models for Image Inpainting

      Wei Yu, Stefan Heber, and Thomas Pock

    • 10

      Image Orientation Estimation with Convolutional Networks

      Philipp Fischer, Alexey Dosovitskiy, and Thomas Brox

    • 11

      Semi-Automatic Basket Catheter Reconstruction from two X-ray views

      Xia Zhong, Matthias Hoffmann, Norbert Strobel, and Andreas Maier

    • 12

      Fast Brain MRI Registration with Automatic Landmark Detection Using a Single Template Image

      Olga V. Senyukova and Denis S. Zobnin

    • 13

      Photorealistic Face Transfer in 2D and 3D Video

      Daniel Merget, Philipp Tiefenbacher, Mohammadreza Babaee, Nikola Mitov, and Gerhard Rigoll

    • YRF1

      Random Forests for 3D Pose Estimation from 2D Images

      Ilya Kostrikov

    • YRF2

      Image Segmentation in Twenty Questions

      Christian Rupprecht

    • NT1

      Discovering Object Classes from Activities

      Abhilash Srikanta, Jürgen Gall (ECCV 2014)

    • NT2

      Stereo Ground Truth with Error Bars

      Daniel Kondermann, Rahul Nair, Stephan Meister, Wolfgang Mischler, Burkhard Güssefeld, Claus Brenner, Bernd Jähne (ACCV 2014)

    • NT3

      Visualizing Tensor Normal Distributions at Multiple Levels of Detail

      A. Abbasloo, V. Wiens, M. Hermann, T. Schultz (TVCG / IEEE VIS 2015)

    • NT4

      Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images

      Carsten Rother (ICCV 2015)

    • NT5

      Selecting Influential Examples: Active Learning with Expected Model Output Changes

      Alexander Freytag, Erik Rodner, and Joachim Denzler (ECCV 2014)

    • NT6

      Traditional Saliency Reloaded: A Good Old Model in New Shape

      Simone Frintrop, Thomas Werner, and Germán Martín García (CVPR 2015)

    • NT7

      Material Classification based on Training Data Synthesized Using a BTF Database

      Michael Weinmann, Juergen Gall, Reinhard Klein (ECCV'14)

    • NT8

      Driven Learning for Driving: How Introspection Improves Semantic Mapping

      R. Triebel, H. Grimmet, R. Paul, I. Posner (ISRR 2013)

    • NT9

      Face detection without bells and whistles

      Markus Mathias, Rodrigo Benenson, Marco Pedersoli, Luc Van Gool (ECCV'14)

    • NT10

      Linguistic Knowledge for Visual Recognition and Natural Language Descriptions of Visual Content (DAGM MVTec Dissertation Award)

      Marcus Rohrbach (DAGM MVTec Dissertation Award)

  • P2 Fri, 09.10. 13:30-15:30 (Poster Session 2)

    • 14

      GraphFlow - 6D Large Displacement Scene Flow via Graph Matching

      Hassan Abu Alhaija, Anita Sellent, Daniel Kondermann, and Carsten Rother

    • 15

      FlowCap: 2D Human Pose from Optical Flow

      Javier Romero, Matthew Loper, and Michael J. Black

    • 16

      3D Facial Landmark Detection: How to Deal with Head Rotations?

      Anke Schwarz, Esther-Sabrina Wacker, Manuel Martin, M. Saquib Sarfraz, and Rainer Stiefelhagen

    • 17

      Enhanced GPT Correlation for 2D Projection Transformation Invariant Template Matching

      Toru Wakahara and Yukihiko Yamashita

    • 18

      Semantic segmentation based traffic light detection at day and at night.

      Vladimir Haltakov, Jakob Mayr, Christian Unger, and Slobodan Ilic

    • 19

      Pose Estimation and Shape Retrieval with Hough Voting in a Continuous Voting Space

      Viktor Seib, Norman Link, and Dietrich Paulus

    • 20

      Fast Approximate GMM Soft-Assign for Fine-Grained Image Classification with Large Fisher Vectors

      Josip Krapac and Siniša Šegvić

    • 21

      Regressor Based Estimation of The Eye Pupil Center

      Necmeddin Said Karakoc, Samil Karahan, and Yusuf Sinan Akgul

    • 22

      Patch-level Spatial Layout for Classification and Weakly Supervised Localization

      Valentina Zadrija, Josip Krapac, Jakob Verbeek, and Siniša Šegvić

    • 23

      A Deeper Look at Dataset Bias

      Tatiana Tommasi, Novi Patricia, Barbara Caputo, and Tinne Tuytelaars

    • 24

      What is Holding Back Convnets for Detection?

      Bojan Pepik, Rodrigo Benenson, Tobias Ritschel, and Bernt Schiele

    • 25

      A Modified Isomap Approach to Manifold Learning in Word Spotting

      Sebastian Sudholt and Gernot A. Fink

    • 26

      Offline Writer Identification Using Convolutional Neural Network Activation Features

      Vincent Christlein, David Bernecker, Andreas Maier, and Elli Angelopoulou

    • YRF3

      Implicit-to-Implicit Registration for Real-Time 3D Reconstruction from RGB-D Data

      Miroslava Slavcheva

    • YRF4

      Superpixel Segmentation: An Evaluation

      David Stutz

    • YRF5

      Robot Arm Tracking with Random Decision Forests

      Felix Widmaier

    • NT11

      U-Net: Convolutional Networks for Biomedical Image Segmentation

      Olaf Ronneberger, Philipp Fischer, Thomas Brox (MICCAI 2015)

    • NT12

      Active Learning and Discovery of Object Categories in the Presence of Unnameable Instances

      Christoph Käding, Alexander Freytag, Erik Rodner, Paul Bodesheim, Joachim Denzler (CVPR 2015)

    • NT13

      Ask Your Neurons: A Neural-based Approach to Answering Questions about Images

      Mateusz Malinowski, Marcus Rohrbach, Mario Fritz (ICCV 2015)

    • NT14

      A TV Prior for High-Quality Local Multi-view Stereo Reconstruction

      Andreas Kuhn, Helmut Mayer, Heiko Hirschmüller, Daniel Scharstein (3DV 2014)

    • NT15

      Human Pose Estimation with Fields of Parts

      Martin Kiefel, Peter Gehler (ECCV 2014)

    • NT16

      The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities

      Hilde Kuehne, Ali Arslan, Thomas Serre (CVPR 2014)

    • NT17

      Expanding Object Detector's Horizon: Incremental Learning Framework for Object Detection in Videos

      Alina Kuznetsova, Sung Ju Hwang, Bodo Rosenhahn, Leonid Sigal (CVPR 2015)

    • NT18

      Extended Pie Menus for Immersive Virtual Environments

      S. Gebhardt, S. Pick, F. Leithold, B. Hentschel, T.W. Kuhlen (IEEE TVCG 2013)

    • NT19

      Dyna: A Model of Dynamic Human Shape in Motion

      G. Pons-Moll, J. Romero, N. Mahmood, M.J. Black (SIGGRAPH 2015)

    • NT20

      Efficient Dense Rigid-Body Motion Segmentation and Estimation in RGB-D Video

      Jörg Stückler, Sven Behnke (IJCV 2015)