Light Field Super-Resolution via Adaptive Feature Remixing
| Autor: | Yeong Jun Koh, Soonkeun Chang, Keunsoo Ko, Chang-Su Kim |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
business.industry
Computer science Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Iterative reconstruction Computer Graphics and Computer-Aided Design Convolution Feature (computer vision) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Angular resolution Artificial intelligence business Image resolution Software Light field Interpolation |
| Zdroj: | IEEE Transactions on Image Processing. 30:4114-4128 |
| ISSN: | 1941-0042 1057-7149 |
| DOI: | 10.1109/tip.2021.3069291 |
| Popis: | A novel light field super-resolution algorithm to improve the spatial and angular resolutions of light field images is proposed in this work. We develop spatial and angular super-resolution (SR) networks, which can faithfully interpolate images in the spatial and angular domains regardless of the angular coordinates. For each input image, we feed adjacent images into the SR networks to extract multi-view features using a trainable disparity estimator. We concatenate the multi-view features and remix them through the proposed adaptive feature remixing (AFR) module, which performs channel-wise pooling. Finally, the remixed feature is used to augment the spatial or angular resolution. Experimental results demonstrate that the proposed algorithm outperforms the state-of-the-art algorithms on various light field datasets. The source codes and pre-trained models are available at https://github.com/keunsoo-ko/ LFSR-AFR |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|