CrossFeat: Bridging Imaging Modalities in Feature Space
zhenjun_zhao · x · 2026-09-02
CrossFeat (ECCV 2026) proposes a framework enabling existing monomodal descriptors to operate across modalities (e.g., RGB-depth, medical imaging). It learns a 'crossing function' in descriptor space and introduces geometry-appearance disentanglement, altering only appearance while preserving geometric properties for better matching.
More from Research
- Loop Launches Supply Chain AI Benchmark AuditBench — daniellewis · 2026-09-02
- 3B TwIL Model Outperforms 120B Open Source Model on Formal Reasoning — Socially-great8275 · 2026-09-02
- Implementing Q-learning in a GDevelop platformer game — tristanbob · 2026-09-02
- Google Open-Sources MAPL-EMIT: Satellite Methane Leak Detection with 84% Accuracy — DynamicWebPaige · 2026-09-02
- Study: ChatGPT caused 21-50% drop in writing variance across the web — maier_ak · 2026-09-02
- AI Polishing Erases Linguistic Identity, Threatens Social Diagnostics — maier_ak · 2026-09-02