Depth Super-Resolution from Explicit and Implicit High-Frequency Features

Xin Qiao, Chenyang Ge, Youmin Zhang, Yanhui Zhou, Fabio Tosi +2 more
3/16/2023
cs.CV

No official code found. Best implementation: wudiqx106/DSR-EI (7 stars, last commit 2023-12-17).

Abstract

We propose a novel multi-stage depth super-resolution network, which progressively reconstructs high-resolution depth maps from explicit and implicit high-frequency features. The former are extracted by an efficient transformer processing both local and global contexts, while the latter are obtained by projecting color images into the frequency domain. Both are combined together with depth features by means of a fusion strategy within a multi-stage and multi-scale framework. Experiments on the main benchmarks, such as NYUv2, Middlebury, DIML and RGBDD, show that our approach outperforms existing methods by a large margin (~20% on NYUv2 and DIML against the contemporary work DADA, with 16x upsampling), establishing a new state-of-the-art in the guided depth super-resolution task.

View on arXivView PDF

Code Implementations(1)

wudiqx106/DSR-EICommunity67%

Code for the paper "Depth Super-Resolution from Explicit and Implicit High-Frequency Features (CVIU 2023)"

70Shell, PythonSep 22, 20232 years ago

Similar Papers

SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-Resolution

87% match1 repo1202023

DSR-Diff: Depth Map Super-Resolution with Diffusion Model

85% match1 repo62023

Cutting-Edge Techniques for Depth Map Super-Resolution

84% match2023

Recurrent Structure Attention Guidance for Depth Super-Resolution

84% match2023

Enhanced Deep Residual Networks for Single Image Super-Resolution

84% match1 repo6762017

Guided Super-Resolution as Pixel-to-Pixel Transformation

83% match1 repo852019

Cite this paper

@article{qiao2023depth,
  title  = {Depth Super-Resolution from Explicit and Implicit High-Frequency Features},
  author = {Xin Qiao and Chenyang Ge and Youmin Zhang and Yanhui Zhou and Fabio Tosi and Matteo Poggi and Stefano Mattoccia},
  year   = {2023},
  eprint = {2303.09307},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.09307v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.09307.svg)](https://codeofpaper.com/paper/2303.09307)

Discussion