The University of Texas at Austin
Computer Science Department

Computer Science 395T
Advanced Geometry Processing

Spring 2017

General Information:

Time: Tuesdays and Thursdays 9:30AM-11:00AM
Place: GDC 4304
Instructor: Qixing Huang

This course will cover topics in the general areas of Digital Geometry Processing and 3D Vision. The course is a graduate-level course that combines instruction of basic material, in-class paper presentations, and a final project. Grading is based on paper presentations (30%) and the final project (70%).

Prereqs: Courses in computer vision and/or machine learning (CS 376 Computer Vision and/or CS 391 Machine Learning, or similar); ability to understand and analyze conference papers in vision and computer graphics; programming required for the final project. Please talk to me or email me if you are unsure if the course is a good match for your background.

Schedule:

Date Topics Notes
Jan. 17 Introduction
Jan. 19 Overview of Geometry Reconstruction and Acquisition
Jan. 24 Overview of Geometric Data Analysis
Jan. 26 Overview of Geometric Modeling, Synthesis and Fabrication
Jan. 31 Image-Based Geometry Reconstruction I Five-point method
Feb. 2 Image-Based Geometry Reconstruction II In-class presentations of final project proposals
Feb. 7 Paper Presentations I (Multi-View Geometry)
Feb. 9 3D Scanning ICP, ICP-Varaints, ICP-Analysis, ICP-Sampling
Feb. 14 Shape Matching
Feb. 16 Mesh Generation
Feb. 21 Paper Presentations II (Geometry Reconstruction)
Feb. 23 Mesh Simplification and Smoothing
Feb. 28 Discrete Differential Geometry
Mar. 2 Shape Deformation
Mar. 7 Paper Presentation III (Mesh Processing)
Mar. 9 Shape Analysis I (Data-Driven Object Matching)
Mar. 21 Shape Analysis II (Data-Driven Shape Segmentation)
Mar. 23 Shape Analysis III (3D Deep Learning I)
Mar. 28 Shape Analysis IV (3D Deep Learning II)
Mar. 30 Shape Analysis V (Guest Lecture by Hao Su)
Apr. 4 Paper presentations IV (Shape Analysis)
Apr. 6 Shape Reconstruction, Modeling and Synthesis I (Assembly-Based)
Apr. 11 Shape Reconstruction, Modeling and Synthesis II (Deep Learning)
Apr. 13 Paper presentations V (Reconstruction, Modeling and Synthesis)
Apr. 18 3D Printing
Apr. 20 Paper presentations VI (3D Printing)
Apr. 25 Graphics Meets AI (Overview)
Apr. 27 Paper presentations VII (Autonomous Geometry Reconstruction)
May 2 Paper presentations VIII (Text-Based Geometry Synthesis)
May 4 Paper presentations IX (Learning to Generate Synthetic Data) Final project report due

Final Project:

The final project is done in groups of 2-3 students. Candidate project ideas will be given in the first three overview lectures (i.e., Lecture 2 to Lecture 4), although you are more than welcome to choose your own ideas. Each project should have an initial proposal, a final report, and a final poster presentation. The project proposal shall describe four key components of a research project (namely Motivation, Technical Merit, Broader Impact, and Project Plan). The final report should be written as an academic research article. A more detailed instruction will be given later.

Paper Presentations:

Each paper presentation session covers 2-3 papers. These papers will be chosen from a candidate paper list. Each paper presentation consists of a presentation session, where one student presents a paper, and a discussion session, where all the students discuss pros and cons of the paper.

Paper Presentations I (Multi-View Geometry):

  • Yasutaka Furukawa and Jean Ponce. "Accurate, Dense, and Robust Multi-View Stereopsis." PAMI, August 2010. Presenter: Lihang Liu
  • John Flynn, Ivan Neulander, James Philbin, and Noah Snavely. "DeepStereo: Learning to Predict New Views From the World's Imagery." CVPR 2016. Presenter: Tianyu Cheng
    		•

    Paper Presentations II (Geometry Reconstruction):

  • Qixing Huang and Dragomir Anguelov. "High Quality Pose Estimation by Aligning Multiple Scans to a Latent Map." IEEE International Conference on Robotics and Automation 2010.Presenter: Joe Langas
  • Richard Newcombe, Dieter Fox, and Steve Seitz. "DynamicFusion: Reconstruction and Tracking of Non-rigid Scenes in Real-Time." CVPR 2015. Presenter: Janice Pan
    		•

    Paper Presentations III (Mesh Processing):

  • Keenan Crane, Clarisse Weischedel, and Max Wardetzky. "Geodesics in Heat: A New Approach to Computing Distance Based on Heat Flow." ACM Transactions on Graphics(SIGGRAPH Proceedings), 32(5), 2013. Presenter: Hari Sridhar
  • Solomon, Justin, Fernando de Goes, Gabriel Peyré, Marco Cuturi, Adrian Butscher, Andy Nguyen, Tao Du, and Leonidas Guibas. "Convolutional Wasserstein Distances: Efficient Optimal Transportation on Geometric Domains." ACM Transactions on Graphics(SIGGRAPH Proceedings), 34(4), 2015. Presenter: Xiangru Huang
  • Beibei Liu, Yiying Tong, Fernando De Goes, and Mathieu Desbrun. "Discrete Connection and Covariant Derivative for Vector Field Analysis and Design." ACM Transactions on Graphics(SIGGRAPH Proceedings), 35(4), 2016. Presenter: Arjun G. Teh
    		•

    Paper Presentations IV (Shape Analysis):

  • Shi-Sheng Huang, Ariel Shamir, Chao-Hui Shen, Hao Zhang, Alla Sheffer, Shi-Min Hu, and Daniel Cohen-Or. "Qualitative Organization of Collections of Shapes via Quartet Analysis". ACM Trans. on Graphics (Special Issue of SIGGRAPH), Vol. 32, No. 4, pp. 71:1-10, 2013. Presenter: Kevin Tai
  • Vladimir G. Kim, Siddhartha Chaudhuri, Leonidas Guibas, and Thomas Funkhouser. "Shape2Pose: Human-Centric Shape Analysis." ACM Transactions on Graphics (Proc. SIGGRAPH), August 2014. Presenter: Xinyi Zhang
  • Ruizhen Hu, Oliver van Kaick, Bojian Wu, Hui Huang, Ariel Shamir, and Hao Zhang. "Learning How Objects Function via Co-Analysis of Interactions". ACM Trans. on Graphics (Special Issue of SIGGRAPH), Vol. 35, No. 4, Article 47, 2016. Presenter: Yi-Hsuan Hsieh

    • Paper Presentations V (Reconstruction, Modeling and Synthesis):

  • Haibin Huang, Evangelos Kalogerakis, and Benjamin Marlin. "Analysis and Synthesis of 3D Shape Families via Deep-Learned Generative Models of Surfaces". Symposium on Geometry Processing 2015. Presenter: Yinan Zhao
  • Jiajun Wu, Chengkai Zhang, Tianfan Xue, William T. Freeman, and Joshua B. Tenenbaum. "Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling." NIPS 2016. Presenter: Brady Zhou
  • Siamak Ravanbakhsh, Jeff Schneider, and Barnabas Poczos. "Deep Learning with Sets and Point Clouds" Under Review for ICLR 2017. Presenter: Soumyajit Gupta

    • Paper Presentations VI (3D Printing):

  • Lin Lu, Andrei Sharf, Haisen Zhao, Yuan Wei, Qingnan Fan, Xuelin Chen, Yann Savoye, Changhe Tu, Daniel Cohen-Or, and Baoquan Chen. "Build-to-Last: Strength to Weight 3D Printed Objects." ACM Transactions on Graphics(SIGGRAPH Proceedings), 33(4), 2014, 97:1--97:10. Presenter: Joshua Vekhter
  • Moritz Bächer, Emily Whiting, Bernd Bickel, and Olga Sorkine-Hornung. "Spin-it: optimizing moment of inertia for spinnable objects." ACM Transactions on Graphics(SIGGRAPH Proceedings), 33(4), 2014, Article No.96.Presenter: Randall Smith
    		•

    Paper Presentations VII (Autonomous Geometry Reconstruction):

  • Kai Xu, Yifei Shi, Lintao Zheng, Junyu Zhang, Min Liu, Hui Huang, Hao Su, Daniel Cohen-Or, and Baoquan Chen. "3D Attention-Driven Depth Acquisition for Object Identification." ACM Transactions on Graphics (SIGGRAPH Asia 2016), 35(6). Presenter: Aron Yu
  • Xinyi Fan, Linguang Zhang, Benedict Brown, and Szymon Rusinkiewicz. "Automated View and Path Planning for Scalable Multi-Object 3D Scanning." ACM Transactions on Graphics (Proc. SIGGRAPH Asia) 35(6), November 2016.Presenter: Arjun Karpur

    • Paper Presentations VIII (Text-Based Geometry Synthesis):

  • Angel X. Chang, Will Monroe, Manolis Savva, Christopher Potts, and Christopher D. Manning. "Text to 3D Scene Generation with Rich Lexical Grounding." In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics (ACL 2015). Presenter: Jaeseong Lee
  • Stephan Streuber, M. Alejandra Quiros-Ramirez, Matthew Q. Hill, Carina A. Hahn, Silvia Zuffi, Alice O’Toole, and Michael J. Black. "Body Talk: Crowdshaping Realistic 3D Avatars with Words." ACM Transactions on Graphics(SIGGRAPH Proceedings), 35(4), 2016, 54:1--54:14. Presenter: Rodolfo Corona
    		•

    Paper Presentations IX (Learning to Generate Synthetic Data):

  • Yuki Koyama, Daisuke Sakamoto, and Takeo Igarashi. "Crowd-Powered Parameter Analysis for Visual Design Exploration." In Proceedings of the 27th annual ACM symposium on User interface software and technology (UIST '14). ACM, New York, NY, USA, 65-74. Presenter: Chia-Chen Hsu
  • Yinda Zhang, Shuran Song, Ersin Yumer, Manolis Savva, Joon-Young Lee, Hailin Jin, and Thomas Funkhouser. "Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks." https://arxiv.org/abs/1612.07429.Presenter: Zhenpei Yang
    		•

    Relevant Courses:

    Intelligient Visual Computing (UMass)
     Shape Analysis of RGB-D Data (Princeton)