OASIS-DC: スパース統合単眼擬似深度の出力レベル整合による汎化可能な深度補完
OASIS-DC: Generalizable Depth Completion via Output-level Alignment of Sparse-Integrated Monocular Pseudo Depth
単眼基盤モデルの相対深度をスパースな距離計測で校正して擬似メトリック深度事前分布を作り、それを洗練ネットワークで補正することで、ラベルが極端に少ない状況でも高精度な深度補完を実現した。
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: Jaehyeon Cho, Jhonghyun An
分類: cs.CV, cs.RO
原文アブストラクト
Recent monocular foundation models excel at zero-shot depth estimation, yet their outputs are inherently relative rather than metric, limiting direct use in robotics and autonomous driving. We leverage the fact that relative depth preserves global layout and boundaries: by calibrating it with sparse range measurements, we transform it into a pseudo metric depth prior. Building on this prior, we design a refinement network that follows the prior where reliable and deviates where necessary, enabling accurate metric predictions from very few labeled samples. The resulting system is particularly effective when curated validation data are unavailable, sustaining stable scale and sharp edges across few-shot regimes. These findings suggest that coupling foundation priors with sparse anchors is a practical route to robust, deployment-ready depth completion under real-world label scarcity.
