単眼深度推定におけるワッサースタイン距離を用いた幾何学的整合性損失のプラグイン化
PLG-IN: Pluggable Geometric Consistency Loss with Wasserstein Distance in Monocular Depth Estimation
異なる視点の画像から得た2つの点群間のワッサースタイン距離を損失として用い、単眼深度・姿勢推定の幾何学的整合性を改善する手法を提案し、KITTIで評価した。
著者: Noriaki Hirose, Satoshi Koide, Keisuke Kawano, Ruho Kondo
分類: cs.CV, cs.RO
原文アブストラクト
We propose a novel objective for penalizing geometric inconsistencies to improve the depth and pose estimation performance of monocular camera images. Our objective is designed using the Wasserstein distance between two point clouds, estimated from images with different camera poses. The Wasserstein distance can impose a soft and symmetric coupling between two point clouds, which suitably maintains geometric constraints and results in a differentiable objective. By adding our objective to the those of other state-of-the-art methods, we can effectively penalize geometric inconsistencies and obtain highly accurate depth and pose estimations. Our proposed method is evaluated using the KITTI dataset.
