Depth Map Inpainting and Super-Resolution based on Internal Statistics of Geometry and Appearance

By Satoshi Ikehata, Ji-Ho Cho, and Kiyoharu Aizawa

Abstract

Depth maps captured by multiple sensors often suffer from poor resolution and missing pixels caused by low reflectivity and occlusions in the scene. To address these problems, we propose a combined framework of patch-based inpainting and super-resolution. Unlike previous works, which relied solely on depth information, we explicitly take advantage of the internal statistics of a depth map and a registered highresolution texture image that capture the same scene. We account these statistics to locate non-local patches for hole filling and constrain the sparse coding-based super-resolution problem. Extensive evaluations are performed and show the state-of-the-art performance when using real-world datasets.

Reference

S. Ikehata, J. Cho, K. Aizawa: "Depth Map Inpainting and Super-Resolution based on Internal Statistics of Geometry and Appearance"; Poster: IEEE International Conference on Image Processing, Melbourne, Australia; 09-15-2013 - 09-18-2013; in: "Proc. of ICIP", IEEE, (2013), 938 - 942.

BibTeX

@inproceedings{TUW-221181,     author = {Ikehata, Satoshi and Cho, Ji-Ho and Aizawa, Kiyoharu},     title = {Depth Map Inpainting and Super-Resolution based on Internal Statistics of Geometry and Appearance},     booktitle = {Proc. of ICIP},     year = {2013},     pages = {938--942},     publisher = {IEEE},     keywords = {depth-map super-resolution, depth-map inpainting, ToF sensor, sparse Bayesian learning},     note = {poster presentation: IEEE International Conference on Image Processing, Melbourne, Australia; 2013-09-15 -- 2013-09-18} } Click into the text area and press Ctrl+A/Ctrl+C or ⌘+A/⌘+C to copy the BibTeX into your clipboard… or download the BibTeX.