重力方向を活用した単眼深度予測
Geo-Supervised Visual Depth Prediction
慣性センサから得られる重力方向の事前知識を単眼深度推定に組み込み、物体表面の法線が重力と整列・直交する性質を利用して精度を向上させた研究。
著者: Xiaohan Fei, Alex Wong, Stefano Soatto
分類: cs.CV, cs.RO
原文アブストラクト
We propose using global orientation from inertial measurements, and the bias it induces on the shape of objects populating the scene, to inform visual 3D reconstruction. We test the effect of using the resulting prior in depth prediction from a single image, where the normal vectors to surfaces of objects of certain classes tend to align with gravity or be orthogonal to it. Adding such a prior to baseline methods for monocular depth prediction yields improvements beyond the state-of-the-art and illustrates the power of gravity as a supervisory signal.
