通过时间一致性挖掘，实现多帧自监督的高效场景流估计
TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation
- 用多帧时序集成策略聚合稳定运动信号
- 在Argoverse 2和nuScenes上提升33%性能
- 速度比优化方法快150倍，适合实时应用
自监督前馈式场景流估计方法具有实时性优势，但仅依赖两帧点对应关系的监督不可靠，尤其在遮挡情况下失效。多帧监督可通过历史帧运动信息提供更稳定的引导，但直接扩展两帧目标无效，因点对应关系跨帧突变导致信号不一致。本文提出TeFlow，通过挖掘时序一致性实现多帧监督。TeFlow引入时序集成策略，从多帧候选池中聚合最一致的运动信号，形成可靠监督。大量实验表明，TeFlow在挑战性的Argoverse 2和nuScenes数据集上达到自监督前馈方法新纪录，性能提升最高达33%。其表现媲美领先优化方法，但推理速度提升150倍。代码与训练权重已在GitHub开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。