Showing 2025Show all
2 papers · 1 filter
cs.CV2025
Multi-View Foundation Models
Leo Segre, Or Hirschorn, Shai Avidan
Foundation models are vital tools in various Computer Vision applications. They take as input a single RGB image and output a deep feature representation that is useful for various…
cs.CV2025
Frequency-Aware Gaussian Splatting Decomposition
Yishai Lavi, Leo Segre, Shai Avidan
3D Gaussian Splatting (3D-GS) enables efficient novel view synthesis, but treats all frequencies uniformly, making it difficult to separate coarse structure from fine detail. Recen…