3.8 Proceedings Paper

Discrete Cosine Transform Network for Guided Depth Map Super-Resolution

出版社

IEEE COMPUTER SOC
DOI: 10.1109/CVPR52688.2022.00561

关键词

-

资金

  1. National Natural Science Foundation of China [61976174]

向作者/读者索取更多资源

Guided depth super-resolution (GDSR) is a key topic in multi-modal image processing, which reconstructs high-resolution depth maps from low-resolution ones with the help of high-resolution RGB images. In this study, the researchers propose a Discrete Cosine Transform Network (DCTNet) to address the challenges in GDSR. The DCTNet outperforms previous methods with a relatively small number of parameters.
Guided depth super-resolution (GDSR) is an essential topic in multi-modal image processing, which reconstructs high-resolution (HR) depth maps from low-resolution ones collected with suboptimal conditions with the help of HR RGB images of the same scene. To solve the challenges in interpreting the working mechanism, extracting cross-modal features and RGB texture over-transferred, we propose a novel Discrete Cosine Transform Network (DCTNet) to alleviate the problems from three aspects. First, the Discrete Cosine Transform (DCT) module reconstructs the multi-channel HR depth features by using DCT to solve the channel-wise optimization problem derived from the image domain. Second, we introduce a semi-coupled feature extraction module that uses shared convolutional kernels to extract common information and private kernels to extract modality-specific information. Third, we employ an edge attention mechanism to highlight the contours informative for guided upsampling. Extensive quantitative and qualitative evaluations demonstrate the effectiveness of our DCTNet, which outperforms previous state-of-the-art methods with a relatively small number of parameters. The code is available at https:// github.com/Zhaozixiang1228/GDSR- DCTNet.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

3.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据