Schedule
| Lecture | Date | Topic | Lecturer | Materials | Assignments |
|---|---|---|---|---|---|
| Lec. 1 | Mon, Aug. 25 | Introduction
Introduction
|
|
|
ps1 out (filtering) |
| Lec. 2 | Wed, Aug. 27 | Filtering
Convolution and cross-correlation
Edge detection Nonlinear filtering |
|
|
|
| Sec. 1 | Fri, Aug. 29 | Linear algebra and filtering |
|
||
| Mon, Sep 1 | No class - Labor Day | ||||
| Lec. 3 | Wed, Sep. 3 | Image pyramids
More filtering
Gaussian pyramid Laplacian pyramid Image statistics (optional) |
|
|
|
| Sec. 2 | Fri, Sep. 5 | Fourier Transform |
|
||
| Lec. 4 | Mon, Sep. 8 | Frequency
Image bases
Fourier transform |
|
|
|
| Lec. 5 | Wed, Sep. 10 | Image formation
Camera models
Projection Plenoptic function |
|
|
ps 1 due ps2 out (frequency) |
| Sec. 3 | Fri, Sep. 12 | Pyramids and Fourier Transform |
|
||
| Lec. 6 | Mon, Sep. 15 | Multi-view geometry
Epipolar geometry
Stereo vision Homographies |
|
|
|
| Lec. 7 | Wed, Sep. 17 | Fitting geometric models
Finding correspondences
Fitting a homography RANSAC Triangulation |
|
|
ps2 due ps3 out (panorama stiching) |
| Sec. 4 | Fri, Sep. 19 | Geometry |
|
||
| Lec. 8 | Mon, Sep. 22 | Structure from motion
Structure from motion
Multi-view stereo Visual SLAM |
|
|
|
| Lec. 9 | Wed, Sep. 24 | Motion estimation
Optical flow
Aperture problem Keypoints |
|
|
Proposal info out |
| Sec. 5 | Fri, Sep. 26 | Project office hours |
|
|
|
| Lec. 10 | Mon, Sep. 29 | Machine learning
Nearest neighbor
Linear regression Overfitting |
|
|
|
| Lec. 11 | Wed, Oct. 1 | Linear classifiers
Logistic regression
Stochastic gradient descent |
|
|
ps3 due ps4 out (intro to ML) |
| Sec. 6 | Fri, Oct. 3 | Machine learning tutorial |
|
||
| Lec. 12 | Mon, Oct. 6 | Neural networks
Nonlinearities
Network structure Regularization |
|
|
|
| Lec. 13 | Wed, Oct. 8 | Optimization
Computation graphs
Backpropagation Momentum |
|
|
ps 4 due ps 5 out (backprop) |
| Sec. 7 | Fri, Oct. 10 | Backpropagation |
|
||
| Mon, Oct 13 | No class - Fall Break | ||||
| Lec. 14 | Wed, Oct. 15 | Convolutional networks
Convolution layers
Pooling Normalization |
|
|
ps5 due ps6 out (scene recognition) |
| Sec. 8 | Fri, Oct. 17 | PyTorch tutorial |
|
||
| Lec. 15 | Mon, Oct. 20 | Object detection
Sliding window
Region-based CNNs Instance segmentation |
|
|
|
| Lec. 16 | Wed, Oct. 22 | Representation learning and language
Autoencoders
Self-supervision Contrastive learning Vision and language |
|
ps6 due ps7 out (image synthesis) |
|
| Sec. 9 | Fri, Oct. 24 | Project office hours |
|
|
|
| Lec. 17 | Mon, Oct. 27 | Image Synthesis with GANs
Texture synthesis
GANs Conditional GANs |
|
||
| Lec. 18 | Wed, Oct. 29 | Transformer |
|
Proposal due ps8 out (diffusion models) |
|
| Sec. 10 | Fri, Oct. 31 | GANs |
|
||
| Lec. 19 | Mon, Nov. 4 | Diffusion Models (I)
Diffusion models for image synthesis
DDPM Latent diffusion models Applications |
|
||
| Lec. 20 | Wed, Nov. 5 | VAEs and Diffusion Models (II) |
|
ps7 due | |
| Sec. 11 | Fri, Nov. 7 | Exam reviews |
|
||
| Lec. 21 | Mon, Nov. 10 | Take home exam |
|
|
|
| Wed, Nov. 12 | No class | ||||
| Sec. 12 | Fri, Nov. 14 | ARC Tutorial (11:30 - 12:30 only) |
|
|
|
| Lec. 22 | Mon, Nov. 17 | Video and recurrent networks
3D convolutions
Recurrent networks LSTMs |
|
ps8 due | |
| Lec. 23 | Wed, Nov. 19 | Bias + image forensics
Fake images
Anomaly detection Supervised detection Datasets Algorithmic fairness |
|
projet guidelines | |
| Sec. 13 | Fri, Nov. 21 | Project office hours |
|
|
|
| Lec. 24 | Mon, Nov. 24 | Light, shading, and color
Shape from shading
Intrinsic images Color perception Neural radiance fields |
|
||
| Wed, Nov 26 | No class - Thanksgiving | ||||
| Fri, Nov 28 | No class - Thanksgiving | ||||
| Lec. 25 | Mon, Dec. 1 | Vision in Robotics |
|
|
|
| Lec. 26 | Wed, Dec. 3 | Generative AI |
|
|
|
| Lec. 27 | Fri, Dec. 5 | Final presentations |
|
|
|
| Lec. 28 | Mon, Dec 8 | Final presentations |
|
|
|
Staff & Office Hours
Office Hours






