Pixel Club: Recovering Hyperspectral Signals from RGB images via Sparse Dictionary Learning

דובר:
בעז ארד (אונ' בן-גוריון)
תאריך:
יום שלישי, 29.11.2016, 11:30
מקום:
חדר 1061, בניין מאייר, הפקולטה להנדסת חשמל

Hyperspectral (HS) images or "hyperspectral data-cubes" contain radiance spectrum information at high spectral resolution for each point in the scene. Until recently, acquiring such information involved expensive, bulky equipment which required long exposure times - making HS imaging impractical for "natural" imaging (ground-level, horizontally viewed scenes). The talk will present a novel methodology, allowing high-accuracy estimation of HS information from unseen scenes using only RGB data acquired from a consumer-grade camera. This is achieved by collection of a highly generalizable HS prior and leveraging the sparsity of HS signals via overcomplete dictionaries.

(see ECCV2016: "Sparse Recovery of Hyperspectral Signal from Natural RGB Images")

בחזרה לאינדקס האירועים