FlowDec: 時間的条件付きフロー修復による頑健な連続環境視覚言語ナビゲーション
FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation
連続環境での視覚言語ナビゲーション(VLN-CE)において、実世界の視覚劣化に対する頑健性を高めるため、時間的文脈を活用した画像修復フレームワークFlowDecを提案した。
著者: Yufei Zhang, Changhao Chen
分類: cs.CV
原文アブストラクト
Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural-language instructions in unseen scenes. While Large Models (LMs) have advanced VLN-CE, their performance remains severely degraded by real-world visual corruptions, a critical yet underexplored domain constraint. We introduce Temporal Conditional Flow Decorruptor (FlowDec), a novel image restoration framework tailored for LM-based VLN-CE. FlowDec integrates a hybrid temporal conditioning strategy to align the generative flow path with historical context and employs action-centroid guided filtering to dynamically assess and integrate outputs. Extensive experiments demonstrate that FlowDec outperforms state-of-the-art decorruption methods in both navigation accuracy and generation latency. Our approach establishes a robust, efficient paradigm for resilient embodied navigation in unpredictable real-world conditions.