This schedule is preliminary and subject to change as the term evolves.

Lecture Date Topic Suggested Reading Assignments
WEEK 1
1 Tue 08/25/2026 Introduction Assignment 0 Out
2 Thu 08/27/2026 3D Representations I
WEEK 2
3 Tue 09/01/2026 3D Representations II Assignment 0 Due
Assignment 1 Out
4 Thu 09/03/2026 Image Formation
WEEK 3
5 Tue 09/08/2026 Single-view 3D: Depth Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer

Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
6 Thu 09/10/2026 Single-view 3D: Objects Learning a predictable and generative vector representation for objects

Occupancy Networks: Learning 3D Reconstruction in Function Space

AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation
WEEK 4
7 Tue 09/15/2026 Single-view 3D: Scenes

Projects: Selection and Timeline
Assignment 1 Due
Assignment 2 Out
8 Thu 09/17/2026 Single-view 3D: Humans and Animals SMPL: A Skinned Multi-Person Linear Model

Embodied Hands: Modeling and Capturing Hands and Bodies Together

End-to-end Recovery of Human Shape and Pose

DOVE: Learning Deformable 3D Objects by Watching Videos
WEEK 5
9 Tue 09/22/2026 Volume Rendering Volume Rendering Digest
10 Thu 09/24/2026 Neural Radiance Fields NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
WEEK 6
11 Tue 09/29/2026 Neural Implicit Rendering Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance

Volume Rendering of Neural Implicit Surfaces

NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction

Objects as volumes: A stochastic geometry view of opaque solids
Assignment 2 Due
Assignment 3 Out
12 Thu 10/01/2026 Differentiable Primitive Rendering (Meshes, Gaussians) Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning

3D Gaussian Splatting for Real-Time Radiance Field Rendering

WEEK 7
13 Tue 10/06/2026 Relightable 3D Representations NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild

PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting
14 Thu 10/08/2026 Dynamic 3D Representations Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes

Nerfies: Deformable Neural Radiance Fields
Project Proposals Due
WEEK 8 - Fall Break
WEEK 9
15 Tue 10/20/2026 Multi-view Transformers: View Synthesis pixelNeRF: Neural Radiance Fields from One or Few Images

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias

TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
Assignment 3 Due
Assignment 4 Out
16 Thu 10/22/2026 Multi-view Transformers: Reconstruction VGGT: Visual Geometry Grounded Transformer

Depth Anything 3: Recovering the Visual Space from Any Views

π³: Permutation-Equivariant Visual Geometry Learning

WEEK 10
17 Tue 10/27/2026 Generative 3D Modeling Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation

pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
18 Thu 10/29/2026 Single-view 3D: A generative approach Trellis: Structured 3D Latents for Scalable and Versatile 3D Generation

SAM3D: 3Dfy Anything in Images

WEEK 11
Tue 11/03/2026 No Class (Democracy Day) Assignment 4 Due
Assignment 5 Out
19 Thu 11/05/2026 Processing Point Clouds I: Classification and Segmentation PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

Point Transformer

Vector Neurons: A General Framework for SO(3)-Equivariant Networks

4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
WEEK 12
20 Tue 11/10/2026 Processing Point Clouds II: Detection Frustum PointNets for 3D Object Detection from RGB-D Data

Deep Hough Voting for 3D Object Detection in Point Clouds

PointPillars: Fast Encoders for Object Detection from Point Clouds
21 Thu 11/12/2026 Processing Meshes SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation

MeshCNN: A Network with an Edge
WEEK 13
22 Tue 11/17/2026 Guest Lecture I Assignment 5 Due
23 Thu 11/19/2026 Guest Lecture II
WEEK 14
24 Tue 11/24/2026 Conclusion
Thu 11/26/2026 Thanksgiving
WEEK 15
25 Tue 12/01/2026 Poster Presentations: I
26 Thu 12/03/2026 Poster Presentations: II
WEEK 16
Wed 12/09/2026 Project Reports Due