Instructor: Manmohan Chandraker

Email: mkchandraker [AT] eng [DOT] ucsd [DOT] edu

Lectures: WF 5-6:20pm on Zoom

Instructor office hours: Thu 1-2pm on Zoom

TA: Zhengqin Li (zhl378@eng.ucsd.edu)

TA office hours: Mon 10-11am on Zoom

TA: You-Yi Jau (yjau@eng.ucsd.edu)

TA office hours: Tue 10-11am on Zoom

Class discussion and message board: Piazza

This course will cover advanced concepts in computer vision. Example topics include 3D reconstruction, face recognition, object detection, semantic segmentation and domain adaptation. The class will be composed of lectures by the instructor, but students will also do one lightning presentation. Grading will be based on presentation (there will be an asynchronous option), assignments and a final exam.

This is an advanced class, covering recent developments in computer vision and will extensively refer to papers. Prior background in computer vision and machine learning is required, through research experience or as covered by CSE 252A, 252B, 250B and similar offerings. Students are encouraged to contact the instructor if unsure about meeting any criteria for enrollment.

This will be a lecture-based course in which the majority of the material will be primarily covered by the instructor. Each student will be asked to give a short presentation on an assigned paper. The presentation will last 5 minutes and an option will be provided to pre-record it. Besides, the class will have three assignments and a final exam.

Grades will be weighted as 60% for assignments, 10% for presentation and 30% for the final exam.

- Feature detection and matching
- Stereo
- Optical flow
- Structure from motion
- Face recognition
- Human pose estimation
- Material and lighting
- Semantic segmentation
- Object detection
- Action recognition
- Domain adaptation

- Lecture [PDF]

- Lecture [PDF]

- Solutions [PDF]

- Lecture [PDF]
- References:

- Lecture [PDF]
- References:

- Lecture [PDF]
- References:

- Lecture [PDF]
- References:

- Lecture [PDF]
- References:

- Instructions [PDF]
- Solutions [Jupyter Notebook] [PDF]

- Lecture [PDF]
- References:
- Five Point Relative Pose
- Three Point Absolute Pose (can ignore algebraic details)
- ORB-SLAM

- Solutions [PDF]

- Lecture [PDF]
- References:

- Lecture [PDF]
- References:

- Lecture [PDF]
- References:

- Instructions [PDF]
- Solutions [Jupyter Notebook] [PDF] [HTML]

- Lecture [PDF]
- References:

- Solutions [PDF]

- Lecture [PDF]
- References:

- Lecture [PDF]
- References:

- Lecture [PDF]
- References:

- Instructions [PDF]

- Lecture [PDF]

- Lecture [PDF]

- Solutions [PDF]

- Lecture [PDF]

- Remote in-class final exam: [PDF]

- Take-home final exam: [PDF]

- Books: There are no books required for this course. Any chapters of books that are extensively referenced in class will be provided as hand-outs.
- Papers: The papers will be provided as PDFs or made available for download through provided links.

Manmohan Chandraker Last modified: Sat, Mar 28, 2020