用基础模型提升深度超分辨率，兼顾精度与泛化能力
DuCos: Duality Constrained Depth Super-Resolution via Foundation Model
- 基于拉格朗日对偶理论，融合多约束与重建目标
- 在多个数据集上超越现有最优方法，显著提升泛化性能
- 适合需要高精度深度图的自动驾驶、机器人场景
我们提出DuCos，一种基于拉格朗日对偶理论的深度超分辨率框架，可灵活整合多种约束与重建目标，提升精度与鲁棒性。首次利用基础模型作为提示，在多样化场景中显著增强泛化能力。提示设计包含两个核心组件：相关性融合（CF）实现提示与深度特征间的精确几何对齐与有效融合；梯度调控（GR）通过强制深度预测与基础模型生成的锐边深度图保持一致性，优化输出。关键的是，这些提示被无缝嵌入拉格朗日约束项，形成协同且有理论依据的框架。大量实验表明，DuCos优于现有最先进方法，在准确率、鲁棒性和泛化性上均取得领先。
原文摘要 · Abstract (English)
We introduce DuCos, a novel depth super-resolution framework grounded in Lagrangian duality theory, offering a flexible integration of multiple constraints and reconstruction objectives to enhance accuracy and robustness. Our DuCos is the first to significantly improve generalization across diverse scenarios with foundation models as prompts. The prompt design consists of two key components: Correlative Fusion (CF) and Gradient Regulation (GR). CF facilitates precise geometric alignment and effective fusion between prompt and depth features, while GR refines depth predictions by enforcing consistency with sharp-edged depth maps derived from foundation models. Crucially, these prompts are seamlessly embedded into the Lagrangian constraint term, forming a synergistic and principled framework. Extensive experiments demonstrate that DuCos outperforms existing state-of-the-art methods, achieving superior accuracy, robustness, and generalization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。