WAVE：反转引导层次以实现由粗到细引导的深度超分辨率

中文摘要 AI 辅助

引导深度超分辨率（GDSR）通常通过卷积层次结构提取RGB引导特征，继承了其由细到粗的偏差。因此，低级空间线索在早期层中显现，而更深层则会抑制那些与真实深度边界不对应的线索，这会导致伪影和边缘模糊。同样的由细到粗偏差也存在于基于语义的方法中，这些方法会早期使用低级令牌，后期使用全局令牌。我们提出WAVE，它引入了多级离散小波变换（ML-DWT）作为一种显式且可解释的特征控制机制，通过以与生成顺序相反的方式使用子带和语义令牌，实现由粗到细的重建。WAVE还利用这些子带分别处理高频和低频内容，从源头过滤那些常导致边界模糊和伪影的误导性RGB颜色与纹理线索，为不透明网络隐式学习的抑制提供了直观的替代方案。WAVE将结构和细节重建分离为专用模块，这些模块：i）对小波子带内部及之间、深度特征和语义先验的交互进行建模；ii）对高频带应用语义门控；iii）通过可逆耦合机制融合模态，防止模型坍缩到单一模态。在多个基准上进行的大量实验表明，WAVE的性能与现有方法相当或更优，在高上采样因子下增益最大，此时低分辨率深度包含的结构最少。

英文摘要

Guided depth super-resolution (GDSR) typically extracts RGB guidance features through convolutional hierarchies, inheriting their fine-to-coarse bias. Thus, low-level spatial cues surface in early layers, leaving the deeper layers to suppress those that do not correspond to true depth boundaries, which risks artifacts and blurred edges. The same fine-to-coarse bias persists in semantics-based methods that consume low-level tokens early and global tokens late. We present WAVE, which introduces a multi-level discrete wavelet transform (ML-DWT) as an explicit and interpretable feature-control mechanism, enabling a coarse-to-fine reconstruction by consuming sub-bands and semantic tokens in reverse of their generation order. WAVE further exploits these sub-bands to treat high- and low-frequency content separately, filtering at its source the misleading RGB color and texture cues that often lead to blurred boundaries and artifacts, offering an intuitive alternative to the suppression learned implicitly by an opaque network. WAVE separates structure and detail reconstruction into dedicated modules that: i) model interactions within and across wavelet sub-bands, depth features, and semantic priors, ii) apply semantic gating to the high-frequency bands, and iii) fuse modalities through an invertible coupling mechanism that prevents collapse onto a single modality. Extensive experiments across multiple benchmarks demonstrate that WAVE matches or outperforms existing methods, with the largest gains at high upsampling factors, where low-resolution depth contains the least structure.

发表机构

• The University of Western Australia（西澳大利亚大学）

机构由 AI 辅助整理，请以论文原文为准。