SOURCE-LINKED INTELLIGENCE

WAVE: Reversing the Guidance Hierarchy for Coarse-to-Fine Guided Depth Super-Resolution

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

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 mec

Read original source ↗ Open in workspace

recordType

paper

region

Global