Abstract | ||
---|---|---|
We present an image compression algorithm that preserves high-frequency details and information of rare occurrences. Our approach can be thought of as image inpainting in the frequency scale space. Given an image, we construct a Laplacian image pyramid, and store only the finest and coarsest levels, thereby removing the middle-frequency of the image. Using a network backbone borrowed from an image super-resolution algorithm, we train our network to hallucinate the missing middle-level Laplacian image. We introduce a novel training paradigm where we train our algorithm using only a face dataset where the faces are aligned and scaled correctly. We demonstrate that image compression learned on this restricted dataset leads to better GAN network [1] convergence and generalization to completely different image domains. We also show that Lapacian inpainting could be simplified further with a few selective pixels as seeds. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/ICIP40778.2020.9191041 | 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) |
Keywords | DocType | ISSN |
Image Inpainting, Super-Resolution | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhang Lingzhi | 1 | 0 | 2.37 |
Pujika Kumar | 2 | 0 | 0.34 |
Manuj Sabharwal | 3 | 28 | 2.72 |
Andy Kuzma | 4 | 0 | 0.34 |
Jianbo Shi | 5 | 10207 | 1031.66 |