流れに任せて：自己教師ありシーンフロー推定
Just Go with the Flow: Self-Supervised Scene Flow Estimation
自動運転シーンで非剛体物体の動きを推定するシーンフローネットワークを、最近傍とサイクル整合性に基づく自己教師あり損失で大規模未ラベルデータから学習し、教師あり手法と同等以上の性能を達成した。
著者: Himangi Mittal, Brian Okorn, David Held
分類: cs.CV, cs.LG, cs.RO, eess.IV
原文アブストラクト
When interacting with highly dynamic environments, scene flow allows autonomous systems to reason about the non-rigid motion of multiple independent objects. This is of particular interest in the field of autonomous driving, in which many cars, people, bicycles, and other objects need to be accurately tracked. Current state-of-the-art methods require annotated scene flow data from autonomous driving scenes to train scene flow networks with supervised learning. As an alternative, we present a method of training scene flow that uses two self-supervised losses, based on nearest neighbors and cycle consistency. These self-supervised losses allow us to train our method on large unlabeled autonomous driving datasets; the resulting method matches current state-of-the-art supervised performance using no real world annotations and exceeds state-of-the-art performance when combining our self-supervised approach with supervised learning on a smaller labeled dataset.
