アンカー付きエピポーラガイダンスによるドリフト耐性ナビゲーションワールドモデル
Drift-Resistant Navigation World Model with Anchored Epipolar Guidance
逐次ロールアウトによるノイズ蓄積と幾何学的ドリフトを防ぐため、疎な未来アンカーを予測し、その間のフレームを生成する新しいワールドモデルを提案。双方向エピポーラ幾何でアンカーを拘束し、長期的な視覚品質と幾何的一貫性を向上させた。
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: Po-Chien Luan, Zimin Xia, Wuyang Li, Yang Gao, Alexandre Alahi
分類: cs.CV, cs.RO
原文アブストラクト
We propose Drift-Resistant Navigation World Model, a generative model that mitigates both perceptual drift and geometric drift in conventional rollout-based navigation world models. Existing methods recursively feed generated content into subsequent steps, causing noise accumulation and degraded predictions, i.e., perceptual drift. Meanwhile, their predictions often deviate from the agent's motion, resulting in geometry drift. We address both types of drift by redesigning world-model prediction as an anchor-guided rollout. Instead of rolling out every frame sequentially, we first predict sparse future anchors that serve as stable long-range targets, and then generate intermediate frames within each chunk conditioned on both past context and future anchors. Importantly, these sparse anchors also provide geometric constraints, supported by bidirectional epipolar geometry, to localize where corresponding content should appear in the intermediate frames. Experiments on four benchmarks demonstrate consistent improvements over strong baselines in long-horizon visual quality, geometric consistency, and multi-view coherence. These gains further translate into improved downstream planning performance under the same planners, highlighting the importance of drift-resistant, geometry-aware prediction for reliable navigation world models.
