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

arXiv: https://arxiv.org/abs/2608.25302 · HTML: https://mlsanity.com/paper/2608.25302/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 30 of 30)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization](https://mlsanity.com/paper/2306.16928/) (2023)
- [Invertible Image Rescaling](https://mlsanity.com/paper/2005.05650/) (2020)
- [Discrete Cosine Transform Network for Guided Depth Map Super-Resolution](https://mlsanity.com/paper/2104.06977/) (2021)
- [Deformable Kernel Networks for Joint Image Filtering](https://mlsanity.com/paper/1910.08373/) (2019)
- [Joint Image Filtering with Deep Convolutional Networks](https://mlsanity.com/paper/1710.04200/) (2017)
- [RGB-D Salient Object Detection with Cross-Modality Modulation and Selection](https://mlsanity.com/paper/2007.07051/) (2020)
- [Guided Depth Super-Resolution by Deep Anisotropic Diffusion](https://mlsanity.com/paper/2211.11592/) (2022)
- [Tri-Perspective View Decomposition for Geometry-Aware Depth Completion](https://mlsanity.com/paper/2403.15008/) (2024)
- [Channel Attention based Iterative Residual Learning for Depth Map Super-Resolution](https://mlsanity.com/paper/2006.01469/) (2020)
- [Detect Anything 3D in the Wild](https://mlsanity.com/paper/2504.07958/) (2025)
- [Joint Implicit Image Function for Guided Depth Super-Resolution](https://mlsanity.com/paper/2107.08717/) (2021)
- [BridgeNet: A Joint Learning Network of Depth Map Super-Resolution and Monocular Depth Estimation](https://mlsanity.com/paper/2107.12541/) (2021)
- [Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution](https://mlsanity.com/paper/2303.08942/) (2023)
- [SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-Resolution](https://mlsanity.com/paper/2312.05799/) (2023)
- [Guided Depth Map Super-resolution: A Survey](https://mlsanity.com/paper/2302.09598/) (2023)
- [High-resolution Depth Maps Imaging via Attention-based Hierarchical Multi-modal Fusion](https://mlsanity.com/paper/2104.01530/) (2021)
- [Symmetric Uncertainty-Aware Feature Transmission for Depth Super-Resolution](https://mlsanity.com/paper/2306.00386/) (2023)
- [Recurrent Structure Attention Guidance for Depth Super-Resolution](https://mlsanity.com/paper/2301.13419/) (2023)
- [Structure Flow-Guided Network for Real Depth Super-Resolution](https://mlsanity.com/paper/2301.13416/) (2023)
- [DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution](https://mlsanity.com/paper/2410.11666/) (2024)
- [DuCos: Duality Constrained Depth Super-Resolution via Foundation Model](https://mlsanity.com/paper/2503.04171/) (2025)
- [C2PD: Continuity-Constrained Pixelwise Deformation for Guided Depth Super-Resolution](https://mlsanity.com/paper/2501.07688/) (2025)
- [Scene Prior Filtering for Depth Super-Resolution](https://mlsanity.com/paper/2402.13876/) (2024)
- [NAIMA: Semantics Aware RGB Guided Depth Super-Resolution](https://mlsanity.com/paper/2604.04407/) (2026)

## Abstract (arXiv)

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.