Skip to Content
CSE5519CSE5519 Advances in Computer Vision (Topic G: 2025: Correspondence Estimation and Structure from Motion)

CSE5519 Advances in Computer Vision (Topic G: 2025: Correspondence Estimation and Structure from Motion)

MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos

link to paper 

  • vanilla Droid-SLAM
  • mono-depth initialization
  • objective movement map prediction
  • two-stage training scheme
Tip

How does the two-stage training scheme help with the robustness of the model? For me, it seems that this paper is just the integration of GeoNet (separated pose and depth) with full regression.

Last updated on
CSE5519 Advances in Computer Vision (Topic A: 2025: Semantic Segmentation)CSE5519 Advances in Computer Vision (Topic I: 2025: Embodied Computer Vision and Robotics)