Advanced Computer Vision

CSE 252C: Advanced Computer Vision, Spring 2019

Instructor: Manmohan Chandraker
Email: mkchandraker [AT] eng [DOT] ucsd [DOT] edu

Lectures: WF 5-6:20pm in CSB 004
Instructor office hours: Thu 5-6pm at CSE 4122

TA: Zhengqin Li (
TA office hours: Tue 3pm-4pm in EBU3B 4127


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 with a participation element too where students will engage through lightning presentations. Grading will be based on participation, presentation, 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.

Course Format and Requirements

This will be a lecture-based course in which the majority of the material will be primarily covered by the instructor. However, each student will be asked to give a short presentation on an assigned paper. Each presentation will last 7 mintues, with 5 minutes for explaining the paper and 2 mintues for questions. Some questions will be asked by the presenter and the others by the audience. Besides, the class will have three assignments and a final exam.

Grades will be weighted as 50% for assignments, 20% for in-class presentation and participation and 30% for the final exam.


The course will cover a diverse range of topics in computer vision, including:


Apr 03: Introduction Apr 05: Overview Apr 10: Background Apr 12: Correspondence Apr 17: Keypoint detection and description Apr 19: Optical flow Homework 1 :
Apr 24: Structure from Motion: I Apr 26: Structure from Motion: II May 01: Robustness and Learning in SFM May 03: Face Recognition: Datasets, Verification, Identification May 08: Face Recognition: Metric Learning, Softmax Variants May 10: Face Alignment Homework 2 : May 15: Human Pose Estimation May 17: 3D Pose and Shape Estimation May 22: Semantic Segmentation: I May 24: Semantic Segmentation: II Homework 3 : May 29: Object Detection: I May 31: Object Detection: II June 05: Review


Manmohan Chandraker
Last modified: Fri, May 31, 2019