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.

翻译：自监督前馈方法在场景流估计中具有实时推理效率，然而其基于两帧点对应关系的监督信号不可靠，且在遮挡场景下常出现失效。多帧监督有潜力通过引入历史帧的运动线索提供更稳定的引导信号，但由于点对应关系在帧间存在剧烈突变导致信号不一致，简单沿用两帧监督目标的方法难以生效。本文提出TeFlow，通过挖掘时序一致性监督信号为前馈模型实现多帧监督。该框架提出时序集成策略：从跨多帧构建的候选池中聚合最具时序一致性的运动线索，形成可靠的监督信号。大量实验表明，TeFlow在具有挑战性的Argoverse 2和nuScenes数据集上以高达33%的性能提升刷新了自监督前馈方法的最优水平。本方法性能与领先的优化类方法相当，但推理速度提升150倍。代码与预训练模型权重已在https://github.com/Kin-Zhang/TeFlow开源。