Score: 1

Stable Single-Pixel Contrastive Learning for Semantic and Geometric Tasks

Published: December 4, 2025 | arXiv ID: 2512.04970v1

By: Leonid Pogorelyuk , Niels Bracher , Aaron Verkleeren and more

Potential Business Impact:

Helps computers understand images by matching points.

Business Areas:
Image Recognition Data and Analytics, Software

We pilot a family of stable contrastive losses for learning pixel-level representations that jointly capture semantic and geometric information. Our approach maps each pixel of an image to an overcomplete descriptor that is both view-invariant and semantically meaningful. It enables precise point-correspondence across images without requiring momentum-based teacher-student training. Two experiments in synthetic 2D and 3D environments demonstrate the properties of our loss and the resulting overcomplete representations.

Country of Origin
🇺🇸 🇩🇪 United States, Germany

Page Count
12 pages

Category
Computer Science:
CV and Pattern Recognition