University Courses
This course was designed from a systematic survey of 11 university courses on world models, 3D vision, SLAM, robot learning and spatial intelligence. They are our coordinate system: every module in the tracks cites the lectures and assignments it draws from.
We link, we don't mirror. All cards below point to the official course pages; materials remain with their authors and institutions. The "Public materials" badge reflects how much of each course is openly accessible (Very High → Very Low). Two courses — Columbia Spatial AI and Harvard GSD Spatial Intelligence — approach spatial intelligence from architecture and human-centered design rather than robotics; they are flagged as complementary perspectives.
Public materials:
University of Pennsylvania
CIS 6280 · World Models
- Probabilistic formulation of world models
- State Space Models & Kalman filtering
- Self-supervised representation learning (JEPA)
- Latent world models, RSSM, Dreamer, TD-MPC
- Diffusion, flow matching & video world models
- +3 more topics
SlidesNotesAssignmentsLabsCodeVideos
💡 The backbone of this course — the first graduate course devoted entirely to world models.
Stanford University
CS231A · Computer Vision: From 3D Perception to 3D Reconstruction and Beyond
- Camera models & calibration
- Epipolar geometry, stereo, structure from motion
- Optimal estimation (Kalman/EKF/UKF)
- Monocular depth estimation
- NeRF & Gaussian Splatting
SlidesNotesAssignmentsLabsCodeVideos
Carnegie Mellon University
16-825 · Learning for 3D Vision
- 3D representations (explicit, implicit, neural)
- Volume rendering & NeRF
- 3D Gaussian Splatting & differentiable rendering
- Dynamic 3D (Nerfies, scene flow fields)
- Multi-view transformers (VGGT, LVSM)
- +1 more topics
SlidesNotesAssignmentsLabsCodeVideos
Massachusetts Institute of Technology
16.485 · Visual Navigation for Autonomous Vehicles (VNAV)
- 3D geometry & Lie groups (SO(3)/SE(3))
- Two-view geometry, RANSAC, bundle adjustment
- Optimization on manifolds, factor graphs
- Visual-inertial odometry (VIO)
- SLAM formulations & incremental solvers
- +1 more topics
SlidesNotesAssignmentsLabsCodeVideos
📄 MIT OCW: CC BY-NC-SA 4.0 · vnav.mit.edu: CC BY 4.0
ETH Zurich / University of Zurich
151-0632-00L / 03SMDINF2039 · Vision Algorithms for Mobile Robotics
- Perspective projection & camera calibration
- Multiple-view geometry, 8-point algorithm, PnP
- Optical flow & KLT tracking
- Place recognition (bag of words)
- Visual-inertial odometry & sensor fusion
- +1 more topics
SlidesNotesAssignmentsLabsCodeVideos
💡 Mini-project: build a full visual odometry pipeline on KITTI/Malaga real data.
University of California, San Diego
Machine Learning Meets Geometry
- 3D reconstruction (single-image & multiview)
- 3D recognition, detection & segmentation
- 6D pose estimation
- Point cloud & mesh processing
- Part-based generative models
- +1 more topics
SlidesNotesAssignmentsLabsCodeVideos
UC Berkeley
CS294-173 · Learning for 3D Vision
- 3D representations (mesh, point cloud, voxel, implicit/SDF)
- Multi-view stereo & COLMAP
- Differentiable renderers (Soft Rasterizer, Mitsuba 2)
- Implicit differentiable rendering (SRN, DVR, IDR)
- View synthesis (NeRF, MPI, SynSin)
- +1 more topics
SlidesNotesAssignmentsLabsCodeVideos
Cornell University
CS 6672 · 3D Vision
- Image formation, epipolar geometry, SfM
- Localization, 6-DoF pose & SLAM
- NeRF & 3D Gaussian Splatting
- DUSt3R & deep multi-view stereo
- Diffusion & text-to-3D (DreamFusion)
- +1 more topics
SlidesNotesAssignmentsLabsCodeVideos
Technical University of Munich (TUM), Computer Vision Group
Practical Course, 10 ECTS · Deep Learning for Spatial AI
- 3D/4D reconstruction & SLAM (VGGT)
- 3D priors with diffusion models (Bolt3D)
- 3D tracking (SpatialTracker)
- Self-supervised learning with 3D priors (RayZer)
- Bundle adjustment for dynamic scenes
- +1 more topics
SlidesNotesAssignmentsLabsCodeVideos
Columbia University (GSAPP)
ARCH A6956-1 · Spatial AI
🏛️ Architecture / Design perspective
- Spatial reasoning & spatial ontology
- Generative AI / LLM agents for space
- Vision & spatial language models
- Metric spaces, distance & positioning
- Connectivity, way-finding and way-signalling
- +1 more topics
SlidesNotesAssignmentsLabsCodeVideos
💡 Architecture / computational-design perspective on spatial intelligence — a complement, not a robotics course.
Harvard University, Graduate School of Design
SCI-6512 · Spatial Intelligence: Designing the Future of Work
🏛️ Human-centered perspective
- Human-centered spatial intelligence
- Sensors & environmental data collection
- Intelligent environments (ethics & implications)
- Multimodal data analysis & visualization
- Human-space / human-building interaction
- +1 more topics
SlidesNotesAssignmentsLabsCodeVideos
💡 Human-centered / smart-environments perspective; only the course description page is public.