Date	Description	Course Materials
Part 0: Course Setup and Logistics
Tuesday, 9/8	Course overview	Lecture slides [pdf] Szeliski book, Chapter 1 Thorpe et al., 1996
Thursday, 9/10	Python, NumPy, and Matplotlib tutorial	Linear algebra [1, 2], probability review [1] NumPy tutorial (via Stanford CS231n) Colab page
Part I: Classical Computer Vision
Tuesday, 9/15	Cameras and geometric image formation	Lecture slides [pdf] Szeliski book, Chapter 2 Wikipedia camera Light stages at USC
Thursday, 9/17	Light, reflectance, color, and sensors	Lecture slides [pdf] Szeliski book, Chapter 2 Surface reflectance, Dror et al., 2001 Chapter 3 of Forsyth and Ponce book Beau Lotto's TED talk
Tuesday, 9/22	Sampling, convolution, Fourier analysis, and image pyramids	Szeliski book, Chapter 3 Hybrid images Non-local means denoising, Buades et al., 2011
Thursday, 9/24	Edges, corners, blobs, and scale space	Szeliski book, Chapter 7.1 Berkeley segmentation dataset
Tuesday, 9/29	Local descriptors and correspondence	Szeliski book, Chapter 7.1 VGG image search
Thursday, 10/1	Transformations, homographies, alignment, and robust estimation	Szeliski book, Chapter 8.1 & 8.2
Tuesday, 10/6	Camera geometry: calibration, pose, and epipolar constraints	Szeliski book, Chapter 11
Thursday, 10/8	Depth and 3D reconstruction: triangulation, stereo, and SfM	Szeliski book, Chapter 12 Middlebury stereo dataset
Tuesday, 10/13	Optical flow and point tracking	Szeliski book, Chapter 9 Lucas-Kanade optical flow
Thursday, 10/15	Midterm 1: classical vision
Part II: Modern Computer Vision
Tuesday, 10/20	From classical recognition to learned representations	Szeliski book, Chapter 6 Bag of Words, HoG, Textons
Thursday, 10/22	Convolutional neural networks for vision	Szeliski book, Chapter 5 ImageNet LeNet, AlexNet, VGGNet, ResNet
Tuesday, 10/27	Convolutional neural networks for vision	Pytorch CNN tutorial
Thursday, 10/29	Vision transformers
Tuesday, 11/3	No class — Election Day
Thursday, 11/5	Self-supervised representation learning	Colorization [1, 2], Context, Jigsaw, Rotation MOCO, SimCLR, BYOL
Tuesday, 11/10	Vision-language foundation models
Thursday, 11/12	Object detection and open-vocabulary localization	Dalal & Triggs, Selective search R-CNN, Fast R-CNN, Faster R-CNN YOLO, SSD
Tuesday, 11/17	Semantic, instance, and promptable segmentation	FCNs UNet, Ronneberger et al., MICCAI 2015 Mask R-CNN, He et al., ICCV 2017, SAM
Thursday, 11/19	Keypoints, articulated pose, and shape	Poselets, Bourdev & Malik, 2010
Tuesday, 11/24	No class — Wednesday schedule followed
Thursday, 11/26	No class — Thanksgiving recess
Tuesday, 12/1	Modern video understanding	Video correspondence - Jabri et al., 2020 Future prediction - Walker et al., 2016
Thursday, 12/3	Diffusion models, generation, and image editing	Inverting deep representations Texture synthesis & style transfer using CNNs, Gatys et al., 2015 Generative adversarial networks, Goodfellow et al., 2020 (CACM version) Deep image prior, Ulyanov et al., 2017 Texture synthesis by non-parametric sampling, Efros & Leung, 1999
Tuesday, 12/8	Midterm 2: modern vision
Thursday, 12/10	Neural rendering, NeRF, Gaussian splatting, and 3D vision	NeRF, Mildenhall et al., 2020 Multi-view CNN PointNet, PointNet++ A deeper look at 3D shape classifiers, Su et al., 2018
Tuesday, 12/15	Reliable vision, research frontiers, and course synthesis
Final-exam period	Project poster/oral presentations