ECE 495: Cameras, Images, and Statistical Inverse Problems

Professor Stanley H. Chan, Purdue University, Spring 2022

Announcements

• 01/06/2022 Classroom changed to MSEE B010.
• 10/01/2021 Course website launched.

Course Information

• Lecture: MWF 10:30am - 11:20am
• Room: MSEE B010 (in-person)
  • Lectures will be recorded via BoilerCast and made available in Brightspace (subject to delays).
• Instructor: Professor Stanley H. Chan
  • Room: MSEE 338
  • Email: stanleychan@purdue.edu
  • Office Hour: After class and by appointment.
• Teaching Assistants:
  • Nick Chimitt, nchimitt@purdue.edu
  • Guanzhe Hong, hong288@purdue.edu
  • Office Hour: By appointment.

Syllabus

• Download Syllabus PDF (200KB)

Lecture Notes

Part 1: Understanding Your Camera

• Lecture Note 1-1: Cameras in the 21st century (PDF, 6MB)
• Lecture Note 1-2: Digital image sensors (PDF, 6MB)
• Lecture Note 1-3: Noise
• Lecture Note 1-4: Signal-to-Noise Ratio (PDF, 580KB)
• Lecture Note 1-5: Dynamic Range (PDF, 2.3MB)

Part 2: Probability and Statistics

• Lecture Note 2-1: Gaussian Random Variables (PDF, 500KB)
• Lecture Note 2-2: Central Limit Theorem (PDF, 820KB)
• Lecture Note 2-3: High-dimensional Random Variables (PDF, 830KB)
• Lecture Note 2-4: Basics of Poisson random variables (PDF, 500KB)
• Lecture Note 2-5: Physics of Photon Arrivals (PDF, 540KB)
• Lecture Note 2-6: Single-Photon and Low Bit-Depth Statistics (PDF, 900KB)

Part 3: Estimation Techniques

• Lecture Note 3-1: Maximum-Likelihood Estimation (PDF, 1.6MB)
• Lecture Note 3-2: Properties of ML Estimation (PDF, 480KB)
• Lecture Note 3-3: Maximum-A-Posterior Estimation (PDF, 588KB)
• Lecture Note 3-4: Minimum Mean-Square Estimation (PDF, 432KB)

Part 4: Denoising

• Lecture Note 4-1: Linear Inverse Problems (PDF, 1MB)
• Lecture Note 4-2: ADMM Algorithm (PDF, 800KB)
• Lecture Note 4-3: Patch Reoccurrence
• Lecture Note 4-4: Smoothing Filters
• Lecture Note 4-5: Variance Stabilizing Transforms
• Lecture Note 4-6: Is Denoising Dead?

Part 5: Learning-based Methods

(Not sure if we will have time to get here.)

• Lecture Note 5-1: Network Unrolling
• Lecture Note 5-2: Knowledge Distillation
• Lecture Note 5-3: One-size-fit-all
• Lecture Note 5-4: Dynamic Scenes

Homework (30%)

There will be six homework assignments. I will drop the worst one. If there is a programming problem, you can choose whatever language you like: MATLAB, Python, Julia, or C++ (though C++ is not recommended).

Homework is due at 11:59pm Eastern Time on the due day. Please submit your homework through Gradescope.

• Gradescope Link: Gradescope

• Late homework will not be accepted.

• Homework 0 (No points): Download PDF (150KB) | Due Jan 12, 2022

• Homework 1: Download PDF (1.3MB) | Due Jan 26, 2022

• Homework 2: Download PDF (300KB) | Due Feb 11, 2022

• Homework 3: Download PDF (300KB) | Due March 2, 2022

• Homework 4: Download PDF (240KB) (Data: See Brightspace) | Due March 23, 2022

• Homework 5: Download PDF (304KB) | Due April 8, 2022

• Homework 6: Download PDF (4MB) | Due April 27, 2022

Quiz (30%)

There will be six quizzes. I will drop the worst one. Each quiz is 30 minutes long. The quizzes are conducted right after the due date of the homework. You will be given a 72-hour window to complete the quiz online. Quizzes will be open-book, open-note, open-computer. However, with only 30 minutes, you probably will not have time to read anything besides answering the questions. So, please do the homework.

• Gradescope Link: Gradescope

• Quiz 0 (No points): Jan 1, 2022 - Jan 12, 2022

• Quiz 1: Jan 27, 2022 - Jan 30, 2022

• Quiz 2: Feb 12, 2022 - Feb 14, 2022

• Quiz 3: March 3, 2022 - March 5, 2022

• Quiz 4: March 24, 2022 - March 26, 2022

• Quiz 5: April 9, 2022 - April 11, 2022

• Quiz 6: April 28, 2022 - April 30, 2022

Seminar Reports (30%)

Attend any THREE of the following seminars and write a report of no more than 2 pages (11pt, Times Roman, 1-inch margins). The grading is based on how much thinking you put into each report.

• Jan 17: Eric Fossum - Quanta Image Sensors (10am ET)
  • Q1: Please summarize the talk in 5-7 sentences.
  • Q2: What is the potential benefit and weakness of QIS relative to SPAD?
  • Q3: Why is photon resolving an important problem for imaging?
  • Q4: According to the speaker, what are the societal issues camera engineers should be aware of?
  • Q5: What is the role of signal processing in QIS?
  • Q6: What made you excited about / inspired you when you attended the talk?
  • Q7: If you could ask a question, what would you ask? Please elaborate.
  • Report due Jan 31, 2022
• Jan 26: Bill Freeman (2:30pm ET)
  • Q1-Q7: Same questions as above, custom to his talk about imaging the earth from the earth and the moon camera.
  • Report due Feb 11, 2022
• Feb 15: Sanjeev Koppal (11:30pm ET)
  • Questions on bio-inspired vision and adaptive LiDAR/cameras.
  • Report due March 1, 2022
• Mar 1: Yaniv Romano (10am ET)
  • Questions on conformal prediction and confidence intervals.
  • Report due March 23, 2022
• Mar 22: Joyce Farrell (1pm ET)
  • Questions on physics-based simulations in camera design.
• Apr 13: Kyros Kutulakos (12pm ET)
  • Questions on light transport and dual-pixel imaging.

These talks are part of the Purdue Computational Imaging Seminar.

Class Participation (10%)

This is a small class and so I will be able to remember every one of you. The purpose of class participation is to encourage intellectual discussions.

• Come to class (no formal attendance, but I will remember you).
• Ask questions.
• Reply to questions in Piazza.
• Talk to the TAs.
• Show enthusiasm about learning.

COVID and Health Related Issues

• Protect Purdue: Follow Protect Purdue instructions at https://protect.purdue.edu/.
• If sick: Please rest and stay home. Lectures are recorded via BoilerCast.
• Masks: Recommended inside the classroom.
• Stress: If you experience stress, please contact the instructor or TAs. We are here to help.

Class Policy

We will follow these class policies:

• Class Policy for ECE 495 and ECE 595ML.