Logos of the MPI Informatik and the Graphics, Vision and Video group

Computer Vision for Computer Graphics

Seminar – Summer Semester 2017

Organizers: Christian Theobalt, Michael Zollhöfer, Weipeng Xu

Organisation | Topics | Format | Format (Detail) | Resources


Subspace Video Stabilization (Liu et al., SIGGRAPH 2013)	Image Style Transfer Using Convolutional Neural Networks (Gatys et al., CVPR 2016)

Overview

Computer Vision strives to develop algorithms for understanding, interpreting and reconstructing information about real-world scenes from image and video data.

Computer Graphics focuses on image synthesis – algorithms to build and edit static and dynamic virtual worlds and to display them in photorealistic or stylised ways.

In recent years, these fields have converged more and more since both disciplines create and exploit models describing the visual appearance of objects and scenes. In this seminar series, we will cover advanced research topics that cross the boundaries between the fields of computer vision and computer graphics. We will concentrate on recent research results that were published at top-tier conferences and journals. This seminar will cover research papers from the following problem fields:

motion estimation and tracking,
multi-view geometry and reconstruction,
computational photography and videography,
reconstruction of static and dynamic 3D scenes, and
advanced image and video processing.

Topics

The following table lists more topics than available weeks – this is to allow some flexibility for the interests of the group to change the course structure. Once every participant has submitted their choice of topics, this list will be updated to show the presenter of each topic.

Click on each topic to show the papers to be discussed or show all papers hide all papers.

Topic and Papers	Presentation
Model-based Teeth Reconstruction (Guest Talk, SIGGRAPH Asia 2016) Model-based Teeth Reconstruction Wu et al. SIGGRAPH Asia 2016	4 May 2017 Presenter: Michael Zollhöfer
Scanning and Deformation (Demo Talk) Real-time Non-rigid Reconstruction using an RGB-D Camera Michael Zollhöfer, Matthias Nießner, Shahram Izadi, Christoph Rhemann, Christopher Zach, Matthew Fisher, Chenglei Wu, Andrew Fitzgibbon, Charles Loop, Christian Theobalt, Marc Stamminger SIGGRAPH 2014 3D Self-Portraits Hao Li, Etienne Vouga, Anton Gudym, Jonathan T. Barron, Linjie Luo, Gleb Gusev SIGGRAPH Asia 2013	11 May 2017 Presenter: Franziska Müller Supervisor: Michael Zollhöfer
Learning Interpretable Representations from Images Deep Convolutional Inverse Graphics Network Kulkarni et al. NIPS 2015 Weakly-supervised disentangling with recurrent transformations for 3D view synthesis Yang et al. NIPS 2015	18 Mai 2017 Presenter: Hossein Hajipour Supervisor: Ayush Tewari
3D Object Generation using CNNs Learning a Predictable and Generative Vector Representation for Objects Girdhar et al. ECCV 2016 Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling Wu et al. NIPS 2016	1 June 2017 Presenter: Maxim Maximov Supervisor: Ayush Tewari
Real-time 3D Human Pose Estimation (Demo Talk) Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose Pavlakos et al. CVPR 2017 VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera Mehta et al. SIGGRAPH 2017	8 June 2017 Presenter: Dushyant Mehta Supervisor: Michael Zollhöfer
Volumetric Reconstruction VolumeDeform: Real-time Volumetric Non-rigid Reconstruction Innmann et al. ECCV 2016 KinectFusion: Real-time dense surface mapping and tracking Newcombe et al. ISMAR 2011	22 June 2017 Presenter: Fei Chen Supervisor: Avishek Chatterjee
Real-time Facial Reenactment Face2Face: Real-time Face Capture and Reenactment Thies et al. CVPR 2016 FaceDirector: Continuous Control of Facial Performance in Video Malleson et al. ICCV 2015	29 June 2017 Presenter: Xueting Li Supervisor: Michael Zollhöfer
Monocular Facial Performance Capture Reconstructing Detailed Dynamic Face Geometry from Monocular Video Garrido et al. SIGGRAPH Asia 2013 Anatomically-Constrained Local Deformation Model for Monocular Face Capture Wu et al. SIGGRAPH 2016	6 July 2017 Presenter: Chitra Singh Supervisor: Pablo Garrido
Appearance and Illumination DeLight-Net: Decomposing Reflectance Maps into Specular Materials and Natural Illumination Georgoulis et al. arXiv Mar 2016 Natural Illumination from Multiple Materials Using Deep Learning Georgoulis et al. arXiv Nov 2016	13 July 2017 Presenter: Alexander Koehn Supervisor: Abhimitra Meka
Style Transfer Image Style Transfer Using Convolutional Neural Networks Gatys et al. CVPR 2016 Artistic Style Transfer For Videos Ruder et al. GCPR 2016	20 July 2017 Presenter: Noshaba Cheema Supervisor: Dushyant Mehta
Holoportation Holoportation: Virtual 3D Teleportation Orts-Escolano et al. UIST 2016 Fusion4D: Real-time Performance Capture of Challenging Scenes Dou et al. SIGGRAPH 2016	27 July 2017 Presenter: Sarah Reszow Supervisor: Nadia Robertini
Body Pose Estimation Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs Marcard et al. CGF 2017 EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras Rhodin et al. Siggraph Asia 2016	–
Hand Tracking Robust Articulated-ICP for Real-Time Hand Tracking Tagliasacchi et al. SGP 2015 Efficient and precise interactive hand tracking through joint, continuous optimization of pose and correspondences Taylor et al. SIGGRAPH 2016	–
Hands and Objects Capturing Hands in Action using Discriminative Salient Points and Physics Simulation Tzionas et al. IJCV 2016 Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input Sridhar et al. ECCV 2016	–
Video Stabilization Subspace Video Stabilization Liu et al. TOG 2011 Bundled Camera Paths for Video Stabilization Liu et al. SIGGRAPH 2013	–
Time-lapse Time-lapse Mining from Internet Photos Martin-Brualla et al. SIGGRAPH 2015 Computational Time-Lapse Video Bennett et al. SIGGRAPH 2007	–
Probabilistic Pose Models for 3D Human Pose Estimation Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video Zhou et al. CVPR 2016 Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image Tomè et al. arXiv 2017	–
3D Hair Modeling from a Single Image AutoHair: Fully Automatic Hair Modeling from a Single Image Chai et al. SIGGRAPH 2016 Single-view Hair Modeling Using a Hairstyle Database Hu et al. SIGGRAPH 2015	–
3D Correspondences FAUST: Dataset and evaluation for 3D mesh registration Bogo et al. CVRP 2014 Point Registration via Efficient Convex Relaxation Maron et al. SIGGRAPH 2016	–
Motion Tracking Dense Human Body Correspondences Using Convolutional Networks Wei et al. CVPR 2016 Volumetric 3D Tracking by Detection Huang et al. CVPR 2016	–
Appearance and Geometry Simultaneous Localization and Appearance Estimation with a Consumer RGB-D Camera Wu et al. TVCG 2016 Recovering Shape and Spatially-Varying Surface Reflectance Under Unknown Illumination Xia et al. SIGGRAPH Asia 2016	–