HW3.pdf - HW3 1 CSE 252A Computer Vision I Fall 2019 Homework 3 1.1 Instructor Ben Ochoa 1.1.1 Assignment published on Tuesday 1.1.2 Due on Tuesday

HW3.pdf - HW3 1 CSE 252A Computer Vision I Fall 2019...

This preview shows page 1 - 3 out of 14 pages.

HW3 October 22, 2019 1 CSE 252A Computer Vision I Fall 2019 - Homework 3 1.1 Instructor: Ben Ochoa 1.1.1 Assignment published on: Tuesday, October 22, 2019 1.1.2 Due on: Tuesday, November 5, 2019 11:59 pm 1.2 Instructions Review the academic integrity and collaboration policies on the course website. This assignment must be completed individually. All solutions must be written in this notebook. This includes the theoretical problems, for which you must write your answers in Markdown cells (using LaTeX when appropriate). Programming aspects of the assignment must be completed using Python in this notebook. If you want to modify the skeleton code, you may do so. It has only been provided as a framework for your solution. You may use Python packages (such as NumPy and SciPy) for basic linear algebra, but you may not use packages that directly solve the problem. If you are unsure about using a specific package or function, then ask the instructor and/or teaching assistants for clarification. You must submit this notebook exported as a PDF. You must also submit this notebook as .ipynb file. Submit both files ( .pdf and .ipynb ) on Gradescope. – You must mark the PDF pages associated with each question in Gradescope. If you fail to do so, we may dock points. It is highly recommended that you begin working on this assignment early. Late policy: assignments submitted late will receive a 15% grade reduction for each 12 hours late (i.e., 30% per day). Assignments will not be accepted 72 hours after the due date. If you require an extension (for personal reasons only) to a due date, you must request one as far in advance as possible. Extensions requested close to or after the due date will only be granted for clear emergencies or clearly unforeseeable circumstances. 1.3 Problem 1: Photometric Stereo, Specularity Removal [20 pts] The goal of this problem is to implement a couple of different algorithms that reconstruct a surface using the concept of Lambertian photometric stereo. Additionally, you will implement the specular removal technique of Mallick et al. , which enables photometric stereo to be performed on certain non-Lambertian materials. You can assume a Lambertian reflectance function once specularities are removed. However, note that the albedo is unknown and non-constant in the images you will use. 1
Image of page 1
As input, your program should take in multiple images along with the light source direction for each image. Each image is associated with only a single light, and hence a single direction. 1.3.1 Data You will use synthetic images and specular sphere images as data. These images are stored in .pickle files which have been graciously provided by Satya Mallick. Each .pickle file contains im1 , im2 , im3 , im4 , . . . images. l1 , l2 , l3 , l4 , . . . light source directions.
Image of page 2
Image of page 3

You've reached the end of your free preview.

Want to read all 14 pages?

  • Winter '08
  • staff

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern

Ask Expert Tutors You can ask You can ask ( soon) You can ask (will expire )
Answers in as fast as 15 minutes