This repo contains the official implementation of ICCV 2025 paper "MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning
-
Updated
Sep 12, 2025 - Python
This repo contains the official implementation of ICCV 2025 paper "MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning
vjepa / vjepa2 / vjepa2.1 PCA visualization utility for dense features and world model inspection.
Add a description, image, and links to the dense-features topic page so that developers can more easily learn about it.
To associate your repository with the dense-features topic, visit your repo's landing page and select "manage topics."