Introduction à la Vision Artificielle 2017/2018
Introduction to Computer Vision 2017/2018

Mathieu Aubry, Karteek Alahari, Ivan Laptev, and Josef Sivic

Course Information

Class time: Thursday 9:00 - 12:00

Room: R

News:

Project presentation schedule is available.
Fill the detailed feedback form .
Check your name is on the list of projects, otherwise send me a mail.
TP4 on Neural Networks is available here in html and here in ipynb.
Optional TP on calibration available here in html and herehttp://imagine.enpc.fr/~aubrym/lectures/introvis17/projects in ipynb (points for this TP will be considered as a bonus). The TP follows closely the slides from session 8.

Third TP available here in html and here in ipynb. Due November 30th.
List of papers for the project available here, with attributions at the end.
Second TP available here in html and here in ipynb. Due November 9th.
First TP available here in html and here in ipynb with instructions (updated version with a few errors fixed). Due october 19th.
Final Project Reports due Jan 11th
Example of internship topics: art catalogues analysis, copied details discovery in Bruegel's works

Assignments

There will befour programming assignments representing 60% of the grade. The supporting materials for the programming assignments projects will be in Python. The optional assignment on calibration will be added to the grade as a bonus.

Final project

The final project will represent 40% of the grade. Each project is based on a paper and a list of suggested papers is available here, with attributions at the end.

You are expected to understand and present the paper, but also to offer some added value, such as experiments of your own, new interesting tests with available code, or comparison with other relevant works. This will have to be adapted depending on the paper. You will have to present your project (10 minutes + questions) and return a short summary (2 pages max) of the essential points that should be readable (and useful) for the other students in the class.

Collaboration policy

You can discuss the assignments and final projects with other students in the class. Discussions are encouraged and are an essential component of the academic environment. However, each student has to work out their assignment alone (including any coding, experiments or derivations) and submit their own report. The assignments and final projects will be checked to contain original material. Any uncredited reuse of material (text, code, results) will be considered as plagiarism and will result in zero points for the assignment / final project. If a plagiarism is detected, the student will be reported to ENS.

Course schedule (subject to change):

Lecture	Date	Instructor	Topic and reading materials.	Slides
1	Sept 14	MA	Introduction, overview, image formation, digital photography	PDF
2	Sept 21	MA	Human vision/perception Camera geometry 1 : projective geometry, camera matrix refs : Forsyth and Ponce "Geometric camera model" chapter Szeliski chapter 2 "Image formation"	PDF
3	Sept 28	MA	Stereo vision Image filtering 1: convolution, derivation, Canny,Bilateral Filter	PDF
4	Oct 5	MA	Image filtering 2: Bilateral Filter and applications, Non-Local-Mean Optical Flow: optical flow equation, Lukas-Kanade, Horn and Schunk, SIFT-flow, large displacement optical flow	PDF
5	Oct 12	MA	Color Segmentation: K-means, GMM, Mean shift	PDF
6	Oct 19	KA	Markov Random Fields: optimization methods (graph-cuts, belief propagation, TRW-S), applications to stereo and segmentation Assignment 1 Due	PDF
7	Oct 26	MA	Camera geometry 2 : camera calibration, multi-view reconstruction	PDF
8	Nov 2 10:30	MA	Review of calibration and practical session	PDF
9	Nov 9	JS	Instance-level recognition Assignment 2 Due	PDF
10	Nov 16	MA	Introduction to category-level recognition / Introduction to CNNs	PDF
11	Nov 23 8h45	KA	Low-level video analysis: tracking, human segmentation and pose	PDF
12	Nov 30	IL	High level video analysis, action recognition Assignment 3 due	PDF
	Dec 7		No lecture
13	Dec 14	MA	CNNs for object detection, analyzing CNNs, using 3D models for image analysis	PDF + visu (~500M)
14	Dec 21	MA	3D shape analysis (ICP, shape geometry, shape descriptors, CNN based) Assignment 4 due Optional TP due	PDF
15	Jan 11	MA	TP feedback Intro to Computer Graphics Some recent advances and open challenges Project reports due	PDF
16	Jan 18	MA	Final projects presentation
17	Jan 25	MA	Final projects presentation

Relevant literature:

[1]	D.A. Forsyth and J. Ponce, "Computer Vision: A Modern Approach", Prentice-Hall, 2nd edition, 2011
[2]	J. Ponce, M. Hebert, C. Schmid and A. Zisserman "Toward Category-Level Object Recognition", Lecture Notes in Computer Science 4170, Springer-Verlag, 2007
[3]	O. Faugeras, Q.T. Luong, and T. Papadopoulo, "Geometry of Multiple Images", MIT Press, 2001.
[4]	R. Hartley and A. Zisserman, "Multiple View Geometry in Computer Vision", Cambridge University Press, 2004.
[5]	J. Koenderink, "Solid Shape", MIT Press, 1990
[6]	R. Szeliski, "Computer Vision: Algorithms and Applications", 2010. Online book.