TeFlow：为自监督前馈场景流估计实现多帧监督
TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation
提出时序集成策略，从多帧候选池中聚合最一致的监督信号，可复用于任何需要从点对应中挖掘可靠监督的自监督3D任务，如场景流、光流或深度估计。
原文依据 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.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自监督前馈场景流估计方法具有实时效率，但其来自两帧点对应的监督不可靠，且在遮挡下常常失效。多帧监督有潜力通过融入过去帧的运动线索来提供更稳定的引导，然而对两帧目标的简单扩展是无效的，因为点对应在帧间剧烈变化，产生不一致的信号。本文提出TeFlow，通过挖掘时序一致的监督，为前馈模型实现多帧监督。TeFlow引入一种时序集成策略，通过从跨多帧构建的候选池中聚合最时序一致的运动线索，形成可靠的监督信号。大量评估表明，TeFlow为自监督前馈方法建立了新的最优性能，在具有挑战性的Argoverse 2和nuScenes数据集上取得高达33%的性能提升。我们的方法与领先的基于优化的方法性能相当，但速度提升了150倍。代码与训练模型权重已开源于https://github.com/Kin-Zhang/TeFlow。
英文原文摘要 1217 字符
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.