DegBins: 基于退化驱动的深度超分辨率
DegBins: Degradation-Driven Binning for Depth Super-Resolution
AI总结:
本文提出DegBins框架,通过退化驱动的分箱方法改进深度超分辨率,利用高维特征空间建模退化关系,通过多阶段优化提升重建精度。
摘要:
深度超分辨率(DSR)旨在从低分辨率深度图恢复高分辨率深度图。通常将该任务建模为学习低维特征空间中高分辨率与低分辨率之间的残差。然而,这种加法形式无法准确捕捉高分辨率与低分辨率之间的复杂关系,特别是在空间变化退化情况下。本文引入DegBins,一种新的DSR框架,利用退化驱动的分箱来自适应增强残差建模。具体而言,DegBins将基于回归的DSR重新建模为混合分类-回归问题,其中残差深度表示为离散深度分箱的线性组合,权重由学习的概率分布加权,从而获得更灵活和表达能力强的表示。此外,DegBins在高维特征空间中建模高分辨率与低分辨率之间的退化关系,使能够自适应调整分箱范围和概率优化,条件于局部退化特性。为逐步提高重建质量,DegBins采用多阶段细化方案,其中每个阶段根据前一步的估计执行更细粒度的分箱划分和概率更新。这种由粗到细的设计有助于更准确的深度恢复,特别是在退化严重或结构复杂区域。在五个基准上的广泛实验表明,DegBins在准确性、鲁棒性和泛化性方面均优于现有最先进方法。
英文摘要:
Depth super-resolution (DSR) aims to recover a high-resolution (HR) depth map from its low-resolution (LR) counterpart. With color image guidance, this task is typically formulated as learning the residual between HR and LR in a low-dimensional feature space. However, this additive formulation is insufficient to accurately capture the complex relationship between HR and LR, especially under spatially varying degradations. In this paper, we introduce DegBins, a novel DSR framework that leverages degradation-driven binning to adaptively enhance residual modeling. Specifically, DegBins reformulates the regression-based DSR as a hybrid classification-regression problem, where the residual depth is represented as a linear combination of discrete depth bins weighted by their learned probability distribution, yielding more flexible and expressive representations. Furthermore, DegBins models the degradation relationship between HR and LR in a high-dimensional feature space, enabling adaptive bin range adjustment and probability optimization conditioned on local degradation characteristics. To progressively improve reconstruction quality, DegBins adopts a multi-stage refinement scheme, where each stage performs finer-grained bin partitioning and probability updating based on the former estimation. This coarse-to-fine design facilitates more accurate depth recovery, particularly in regions with severe degradations or complex structural variations. Extensive experiments across five benchmarks demonstrate that DegBins consistently outperforms existing state-of-the-art methods in terms of accuracy, robustness, and generalization.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。