arrow
返回

Improved Upsampling Based Depth Image Super-Resolution Reconstruction

delete2023-01-01
delete0
delete
OA
AI
Y
Yanming Ye *
M
Mengxiong Zhou
Z
Zhanyu Wang
X
Xingfa Shen
DOI:10.1109/ACCESS.2023.3274966delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Constrained by current sensing technology, depth camera only acquires a low-resolution depth image that does not meet actual requirements. To solve this problem, this paper take a divide-and-conquer strategy to synthesize a high-resolution depth image from a low-resolution range image under the guidance of a registered high-resolution color image. Initially, the depth image is divided into planar areas and edge regions. For different zones, we exploit different methods to interpolate the missing depths. At planar area, the linear interpolation method is employed to perform upsampling. At edge region, a segmentation-separation upsampling method is used to interpolate the missing values. Then the upsampling result are refined on the Depth CNN that is built in this paper. We conduct extensive experiments on the benchmark database and real world data with various upsampling rates to illustrate the upsampling ability of our method. The comparison with classical super-resolution algorithms demonstrates that our upsampling algorithm achieves the best quality with fewer artifacts and our depth CNN outperforms the most state-of-the-art methods in terms of qualitative and quantitative evaluations.
Keyword:
Image edge detection
Image resolution
Optical filters
Image reconstruction
Image color analysis
Interpolation
Image segmentation
Depth image
upsampling
super-resolution reconstruction
edge guided

期刊

IEEE Access 封面图
IEEE Access
IF:
3.6
论文数:
9.8W
被引数:
29.4W

机构

H
Hangzhou Dianzi University
学者数:
1.3W
论文数: 9.6K
被引数: 7.5K
C
Changshu Institute of Technology
学者数:
2.2K
论文数: 1.8K
被引数: 3
引用论文

引用论文

Polypropylene/graphene nanosheet nanocomposites by in situ polymerization: Synthesis, characterization and fundamental properties
err2013-07-01
err0
PREAI
errMarcéo A. Milani; Darío González; Raúl Quijada; Nara R.S. Basso; Maria L. Cerrada; Denise S. Azambuja; Griselda B. Galland
err分享
err收藏
err分享
err收藏
DAEANet: Dual auto-encoder attention network for depth map super-resolution
err2021-09-01
err12
PREAI
errCao, Xiang; Luo, Yihao; Zhu, Xianyi; Zhang, Liangqi; Xu, Yan; Shen, Haibo; Wang, Tianjiang; Feng, Qi
err分享
err收藏
Involvement of the central nervous system in non-hodgkin's lymphoma
err1975-07-01
err0
errOAAI
errIvan P. Law; Fred R. Dick; Johannes Blom; Patrick R. Bergevin
err分享
err收藏
err分享
err收藏
Hierarchical Features Driven Residual Learning for Depth Map Super-Resolution
err2019-05-01
err151
PREAI
errGuo, Chunle; Li, Chongyi; Guo, Jichang; Cong, Runmin; Fu, Huazhu; Han, Ping
err分享
err收藏
Depth Map Recovery Based on a Unified Depth Boundary Distortion Model
err2022-01-01
err9
PREAI
errWang, Haotian; Yang, Meng; Lan, Xuguang; Zhu, Ce; Zheng, Nanning
err分享
err收藏
学者 查看更多内容