Machine Learning Meets Geometry
CSE291 (8)  Winter 2022
Lecture Notes of 2021 Winter (Old, link)
Lecture Notes of 2022 Winter (Ongoing)
Section 1 
Theories of Geometry 

1/4

Curve Theory, PDF (2022 ver), Annotated PDF (2021 ver)  overview of the course, logistics, curve theory 
1/7 1/11

Curve Theory (cont), Surface Theory  differential map, normal curvature, principal curvature 
1/13

Surface Theory (II)  shape operator, first fundamental form, isometry, fundamental theorem of surfaces 
1/18

Mesh and Point Cloud  polygonal mesh, point cloud 
1/20

Rotation and SO(3)  rotation matrix, euler angle, angleaxis, quaternion 
Section 2 
3D Deep Learning 

Section 2.1 
3D Reconstruction 

1/25, 1/27

Learningbased MVS  learningbased MVS, NeRF 
2/1

Single Image to 3D  EMD, Chamfer, mesh deformation 
Section 2.2 
3D Data Understanding 

2/3

3D Backbone Networks  Volumetric CNN 
2/8

3D Backbone Networks  PointNet 
2/10, 2/15

6D Pose Estimation  ICP, Umeyama's method, direct method 
2/17

3D Detection  
2/22

3D Instance Segmentation  topdown approach, bottomup approach 
2/24

Intrinsicsbased Analysis  geodesic distance, dijkstra's algorithm for geodesics, learningbased method for geodesics, applications 
Section 2.3 
Structured 3D Learning 

3/3

Deformation Models  surface deformation, space deformation, skeleton skinning 
Section 2.4 
Geometry Processing and Collection Analysis 

3/8

Surface Reconstruction  explicit and implicit method for surface reconstruction 