| Dates |
Wednesdays (11:30 - 12:20) |
Fridays (10:30 - 12:20) |
Assignments |
| 1/4 & 1/6 |
 |
Introduction
|
|
 |
Neural networks
|
|
|
| 1/11 & 1/13 |
 |
Convolutional neural networks (CNNs)
|
|
 |
Training CNNs
|
|
|
| 1/18 & 1/20 |
 |
Classical approach (features)
|
|
 |
Classical approach (bag of words)
|
|
Assig. 1 due (1/17) |
| 1/25 & 1/27 |
 |
Detection CNNs
|
|
 |
Segmentation CNNs
|
|
|
| 2/1 & 2/3 |
|
Segmentation CNNs
|
|
 |
Metric learning techniques
|
|
Assig. 2 due (1/31) |
| 2/8 & 2/10 |
 |
CNN applications
|
|
|
CNN applications
|
|
|
| 2/15 & 2/17 |
 |
RNN and GNN
|
|
 |
Transformer and GAN
|
|
|
| 2/22 & 2/24 |
 |
Break
|
|
|
Break
|
|
|
| 3/1 & 3/3 |
 |
Self-supervised learning
|
|
 |
Image homographies
|
|
Assig. 3 due (2/28) |
| 3/8 & 3/10 |
 |
Camera models
|
|
|
Camera models
|
|
|
| 3/15 & 3/17 |
|
 |
Two-view geometry
|
|
Assig. 4 due (3/16) |
| 3/22 & 3/24 |
 |
Stereo
|
|
 |
Structure from Motion/SLAM
|
|
|
| 3/29 & 3/31 |
|
Multi-View Stereo (MVS)
|
|
 |
Learning-based MVS
|
|
|
| 4/5 & 4/7 |
|
|
Break
|
|
Assig. 5 due (4/4)
|