16-385 Computer Vision, Spring 2020
|Time:||Mondays, Wednesdays noon - 1:20 pm|
|Location:||Margaret Morrison A14|
|Instructor:||Ioannis (Yannis) Gkioulekas|
|Teaching Assistants:||Anand Bhoraskar, Prakhar Kulshreshtha|
This course provides a comprehensive introduction to computer vision. Major topics include image processing, detection and recognition, geometry-based and physics-based vision and video analysis. Students will learn basic concepts of computer vision as well as hands on experience to solve real-life vision problems.
This course requires familarity with linear algebra, calculus, basic probability, as well as programming. In particular, the following courses serve as prerequisite:
Matlab will be used for project assignments and will be covered as part of the introduction to the course.
Readings will be assigned from the following textbook (available online for free):
Additional readings will be assigned from relevant papers. Readings will be posted at the last slide of each lecture.
The following textbooks can also be useful references for different parts of the class, but are not required:
Your final grade will be made up from:
Programming assignments: Programming assignments (PAs) will require implementing a significant computer vision algorithm. Some of them will also have a small theory component relevant to the implementation. Programming will be done in Matlab (PA1) and Python (PA2-7).
Take-home quizzes: Take-home quizzes (TQs) will require solving two-three theory questions related to the corresponding week's two lectures. Answers will need to be typed in LaTeX.
Late days: For the programming assignments, students will be allowed a total of six free late days. Any additional late days will each incur a 10% penalty.
Missed quizzes: For the take-home quizzes, students will be allowed to completely skip a total of three quizzes without penalty. For students that submit more than eight quizzes, only the best eight will be counted towards their grade. There are no free late days for quizzes, and any late quiz will receive zero credit.
Submitting homework: We use Canvas for submitting and grading homeworks.
We use Piazza for class discussion and announcements.
Email: Please use  in the title when emailing the teaching staff!
Office hours: All office hours are at the Smith Hall 200 conference room.
Feel free to email us about scheduling additional office hours.
The following syllabus is tentative and will most likely change during the semester. Slides will be updated on this site after each lecture.
|M, Jan 13||Introduction||pdf, pptx|
|W, Jan 15||Image filtering||pdf, pptx|
|M, Jan 20||No class (Martin Luther King day)|
|W, Jan 22||Image pyramids and Fourier transform||pdf, pptx||PA1 out|
|M, Jan 27||Hough transform||pdf, pptx||TQ1 out|
|W, Jan 28||Feature and corner detection||pdf, pptx|
|M, Feb 3||Feature descriptors and matching||pdf, pptx||TQ1 due, TQ2 out|
|W, Feb 5||2D transformations||pdf, pptx||PA1 due, PA2 out|
|M, Feb 10||2D transformations (continued)||pdf, pptx||TQ2 due, TQ3 out|
|W, Feb 12||Image homographies||pdf, pptx|
|Su, Feb 16||TQ4 out|
|M, Feb 17||Camera models||pdf, pptx||TQ3 due|
|W, Feb 19||Camera models (continued)||pdf, pptx||PA2 due, PA3 out|
|Su, Feb 23||TQ4 due, TQ5 out|
|M, Feb 24||Two-view geometry||pdf, pptx|
|W, Feb 26||Stereo||pdf, pptx|
|Su, Mar 1||TQ5 due, TQ6 out|
|M, Mar 2||Radiometry and reflectance||pdf, pptx|
|W, Mar 4||More on radiometry||pdf, pptx||PA3 due|
|M, Mar 9||No class (spring break)|
|W, Mar 11||No class (spring break)|
|M, Mar 16||No class (Covid-19 transition)|
|W, Mar 18||Photometric stereo and shape from shading||pdf, pptx||PA4 out|
|Su, Mar 22||TQ6 due, TQ7 out|
|M, Mar 23||Image processing pipeline||pdf, pptx|
|W, Mar 25||Image classification||pdf, pptx||PA4 due, PA5 out|
|Su, Mar 29||TQ7 due, TQ8 out|
|W, Mar 30||Bag of works||pdf, pptx||PA4 due, PA5 out|
|W, Apr 1||Neural networks||pdf, pptx|
|Su, Apr 5||TQ9 out|
|M, Apr 6||More neural networks||pdf, pptx||TQ8 due|
|W, Apr 8||Convolutional neural networks||pdf, pptx||PA5 due, PA6 out|
|Su, Apr 12||TQ10 out|
|M, Apr 13||More convolutional neural networks||pdf, pptx||TQ9 due|
|W, Apr 15||Optical flow||pdf, pptx|
|F, Apr 17||Alignment||pdf, pptx|
|Su, Apr 19||TQ10 due|
|M, Apr 20||Tracking||pdf, pptx|
|W, Apr 22||Segmentation and graph-based techniques||pdf, pptx||PA6 due, PA7 out, TQ11 out|
|Su, Apr 26|
|M, Apr 27||Segmentation||pdf, pptx|
|W, Apr 29||Structure from motion and wrap-up||pdf1/pdf2, pptx1/pptx2|
|Su, May 3||PA7 due, TQ11 due|
These lecture notes have been pieced together from many different people and places. Special thanks to colleagues for sharing their slides: Kris Kitani, Bob Collins, Srinivasa Narashiman, Martial Hebert, Alyosha Efros, Ali Faharadi, Deva Ramanan, Yaser Sheikh, and Todd Zickler. Many thanks also to the following people for making their lecture notes and materials available online: Steve Seitz, Richard Szeliski, Larry Zitnick, Noah Snavely, Lana Lazebnik, Kristen Grauman, Yung-Yu Chuang, Tinne Tuytelaars, Fei-Fei Li, Antonio Torralba, Rob Fergus, David Claus, and Dan Jurafsky.