Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
This work addresses the need for fast and accurate super-resolution in resource-aware applications, representing an incremental improvement over existing convolutional neural network methods.
The paper tackles the problem of single-image super-resolution by proposing the Laplacian Pyramid Super-Resolution Network (LapSRN), which progressively reconstructs high-resolution images without bicubic interpolation, achieving high-quality reconstruction with favorable speed and accuracy compared to state-of-the-art methods.
Convolutional neural networks have recently demonstrated high-quality reconstruction for single-image super-resolution. In this paper, we propose the Laplacian Pyramid Super-Resolution Network (LapSRN) to progressively reconstruct the sub-band residuals of high-resolution images. At each pyramid level, our model takes coarse-resolution feature maps as input, predicts the high-frequency residuals, and uses transposed convolutions for upsampling to the finer level. Our method does not require the bicubic interpolation as the pre-processing step and thus dramatically reduces the computational complexity. We train the proposed LapSRN with deep supervision using a robust Charbonnier loss function and achieve high-quality reconstruction. Furthermore, our network generates multi-scale predictions in one feed-forward pass through the progressive reconstruction, thereby facilitates resource-aware applications. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of speed and accuracy.