TeFlow: 時間的一貫性を活用したマルチフレーム自己教師ありフィードフォワードシーンフロー推定
TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation
複数フレームの時間的に一貫した動き手がかりを集約することで、自己教師ありフィードフォワード型シーンフロー推定の精度を大幅に向上させた手法を提案。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Qingwen Zhang, Chenhan Jiang, Xiaomeng Zhu, Yunqi Miao, Yushan Zhang, Olov Andersson, Patric Jensfelt
分類: cs.CV, cs.RO
原文アブストラクト
Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks down under occlusions. Multi-frame supervision has the potential to provide more stable guidance by incorporating motion cues from past frames, yet naive extensions of two-frame objectives are ineffective because point correspondences vary abruptly across frames, producing inconsistent signals. In the paper, we present TeFlow, enabling multi-frame supervision for feed-forward models by mining temporally consistent supervision. TeFlow introduces a temporal ensembling strategy that forms reliable supervisory signals by aggregating the most temporally consistent motion cues from a candidate pool built across multiple frames. Extensive evaluations demonstrate that TeFlow establishes a new state-of-the-art for self-supervised feed-forward methods, achieving performance gains of up to 33\% on the challenging Argoverse 2 and nuScenes datasets. Our method performs on par with leading optimization-based methods, yet speeds up 150 times. The code is open-sourced at https://github.com/Kin-Zhang/TeFlow along with trained model weights.
