Light Field Super-Resolution via Adaptive Feature Remixing

Keunsoo Ko
Korea University

Yeong Jun Koh
Chungnam University

Soonkeun Chang
Samsung Electronics

Chang-Su Kim
Korea University


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.


Keunsoo Ko, Yeong Jun Koh, Soonkeun Chang, and Chang-Su Kim, "Light Field Super-Resolution via Adaptive Feature Remixing," accepted to IEEE Trans. Image Process. (TIP), 2021.
[paper] [code]