幾何視覚arXiv:2303.12157
深度共分散関数の学習
Learning a Depth Covariance Function
RGB画像から深度関数の事前分布や予測分布を定義する共分散関数を学習し、深度補完・バンドル調整・単眼高密度視覚オドメトリに応用した。
著者: Eric Dexheimer, Andrew J. Davison
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
We propose learning a depth covariance function with applications to geometric vision tasks. Given RGB images as input, the covariance function can be flexibly used to define priors over depth functions, predictive distributions given observations, and methods for active point selection. We leverage these techniques for a selection of downstream tasks: depth completion, bundle adjustment, and monocular dense visual odometry.
