Lecture slides will appear here: intro-cv-spring24
Link to the lecture recordings will be posted on piazza.

Date Lecture Readings
2/1 #1 : Introduction and logistics

Module 1: Image Formation
2/6 #2 : Light and color: I
- Spectral basis of light
- Color perception in the human eye

2/8 #3 : Light and color: II
- Tristimulus theory and color spaces
- Color phenomenon

2/13 #4 : Guest speaker: Hadar Elor, "Leveraging Multimodal Foundation Models for Exploring the 3D World"

2/15 #5 : Image formation: I
- Pinhole camera model
- Qualitative properties
  • Szeliski book, Chapter 2

2/20 #6 : Python tutorial (TAs)

2/22 No class (Moday schedule). Homework 2 released (due 3/7)
2/27 #7 : Image formation: II
- Cameras with lenses
- Lens phenomenon
  • Szeliski book, Chapter 2

Module 2: Image Processing and Alignment
2/29 #8 : Digital image representation
- Analog and digital color sensing
- Alignment and demosacing
- Spatial and bightness quantization
- Color displays and colormaps

3/5 #9 : Image processing: I
- Improving brightness and contrast
- Filtering and convolution
- Smoothing
  • Szeliski book, Chapter 3

3/7 #10 : Image processing: II
- Sharpening
- Edge detection
  • Szeliski book, Chapter 3

3/12 Midterm exam in class
3/14 #11 : Guest speaker: Cheng Phoo, Toward Perception Models Beyond Internet Applications
Note: The talk was rescheduled to Friday, 3/15
  • Homework 3 released (due 4/4)

3/19 No class (Spring Break)
3/21 No class (Spring Break)
3/26 #12 : Corners
- Local descriptors
- Simple corner detector
- Harris corner detector
- The second moment matrix
  • Szeliski book, Chapter 7

3/28 #13 : Corners, blobs
- The second moment matrix
- Invariance and equivariance
- Scale equivariant features
  • Szeliski book, Chapter 7

4/2 #14 : Blobs, feature matching, model fitting
- Image pyramid and scale-space
- Feature descriptors
- Matching and ratio test

4/4 #15 : Model fitting, transformations, alignment
- Model fitting using RANSAC - Image transformations
- Transformations from matching
- Image warping

4/9 #16 : Optical flow
- Motion field
- Lucas-Kanade optical flow
- Depth from disparity
- Structured light and the Kinect sensor
  • Szeliski book, Chapter 8

Module 3: Image Understanding
4/11 #17 : Recognition by alignment
- Instance matching
- Vocabulary trees
- Low distortion correspondences
- Structure from motion

4/16 #18 : Introduction to recognition
- What is recognition?
- Brief history of recognition
- Current trends
  • Szeliski book, Chapter 6

4/18 #19 : Representations
- The machine learning framework
- Role of representations
- Two classical representations (HOG and BoVW)

4/23 #20 : Classical machine learning
- Decision trees
- Nearest neighbor classifiers
  • Szeliski book, Chapter 5

4/25 #21 : Guest speaker: Huaizu Jiang, Towards High-fidelity Human Motion Generation

4/30 #22 : Classical machine learning
- Perceptrons
- Learning as optimization
- Linear classifiers
  • Szeliski book, Chapter 5

5/2 #23 : Object detection
- Sliding window detectors
- Region-based detectors
- Datasets and benchmarks

5/7 #24 : Object detection
- Sliding window detectors
- Region-based detectors
- Datasets and benchmarks

5/9 #25 : Deep learning
- Learning via backpropagation
- LeNet and AlexNet
- Visualizing filters in AlexNet
  • Szeliski book, Chapter 5

5/15 Final exam (LGRC A301, 1pm-3pm)