Save this video free

Princeton Intro to Robotics (Fall 2026) | Lecture 15: SLAM with VGGT

Introduction to Robotics @ Princeton · 46:35 · Watch on YouTube

Part of Princeton University ROB 345. See all 15 lectures and search them

These notes were made with YouTube Collector. Paste any YouTube link and get the same: a summary, chapters and a searchable transcript.

Overview

Princeton’s SLAM lecture explains how VGGT maps uncalibrated RGB image sequences to camera intrinsics and poses, depth maps, world-coordinate point maps, and learned correspondence features. It covers VGGT’s training recipe, including more than 10 million frames, a 1.2-billion-parameter vision transformer, and uncertainty-weighted losses, then compares its speed and reconstruction quality with classical SLAM and introduces MapAnything’s metric-scale estimates and extensions for large, semantic maps.

Key takeaways

Chapters

0:00 VGGT Inputs, Camera Estimates, and World-Frame Point Maps
5:30 Bundle Adjustment Versus VGGT’s Learned Reconstruction
10:40 VGGT Training Data: Sensors, COLMAP, and Synthetic Scenes
18:30 VGGT’s Vision Transformer and Alternating Attention
25:11 Four VGGT Training Losses and Per-Pixel Uncertainty
28:39 Chamfer-Distance Results, Bundle-Adjustment Refinement, and Applications
35:55 MapAnything Adds Metric Scale to Uncalibrated Reconstruction
43:03 Limits of Single-View Geometry and Scaling Maps to Large Scenes
45:07 Combining VGGT Geometry with Semantic Maps for Robots

Keep these chapters and the full searchable transcript in your own library.

Transcript excerpt

0:10 All right, I think we'll go ahead and get started. So today is actually our last lecture on this second module on slam. In the next lecture, we'll start our discussion of machine learning for robotics. I guess in some sense we've already started because this last part of slam actually involves quite a bit of learning as we'll see today. In the last lecture, I introduced VGGT. This is the main method that we're talking about when it comes to visual slam. This is a pretty recent paper, so just from about a year and a half ago that they released it. And it's from folks at Meta and the University of Oxford. Maybe just as a quick reminder, I guess this was the demo. So you take some sequence of images from any camera and then VGGT will create a map for you in

0:58 the form of a point cloud and it'll tell you where the camera went in the scene in the different points in time. And I just want to kind of quickly recap the problem definition we had when we talked about visual slam. So the inputs are pretty simple. So just a sequence of capital N RGB images that you give to the system. And I guess the key kind of property of VGGT and systems like it is that you don't make any assumptions about the camera. So you don't have to do some camera calibration beforehand. You can if you want to, and that can help potentially improve some of the results, but there's no necessity to to do that. And the outputs, so there were four outputs that we talked about. So the

1:46 first one is camera intrinsics and extrinsics. So VGGT will basically estimate what the properties of your camera are. So it's focal length or

This is the start of the transcript. Save this video free for the whole transcript, searchable and time-coded.

In this course

Related notes

Summary, takeaways, and chapters were generated by AI from the video's transcript and may contain errors. The video belongs to its creator, Introduction to Robotics @ Princeton.

Want the full transcript?

Save this video in YouTube Collector to get its complete searchable transcript, your own AI summaries, and a library that keeps every video you collect in one place.