4 papers
SwAIther-Precip: Lead-Time-Aware Bias Correction Enables Kilometer-Scale Downscaling of Global AI Precipitation Forecasts over Switzerland
Dan Assouline, Erwan Koch, Federico Amato +5
Skillful medium-range precipitation forecasting at kilometer scale remains challenging over complex terrain because precipitation arises from multiscale nonlinear processes that gl…
PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer
David Picard, Nicolas Dufour, Lucas Degeorge +14
This paper introduces the Polynomial Mixer (PoM), a novel token mixing mechanism with linear complexity that serves as a drop-in replacement for self-attention. PoM aggregates inpu…
Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regression
Thibaut Loiseau, Guillaume Bourmaud, Vincent Lepetit
Pre-training techniques have greatly advanced computer vision, with CroCo's cross-view completion approach yielding impressive results in tasks like 3D reconstruction and pose regr…
RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges
Thibaut Loiseau, Guillaume Bourmaud
Camera pose estimation is crucial for many computer vision applications, yet existing benchmarks offer limited insight into method limitations across different geometric challenges…