Details

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
5/5 based on 1 votes.
Abstract: 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.
,
Submitted by elementlist on Apr 16, 2017 (Edited Apr 16, 2017)
43 views. Averaging 0 views per day.

Comments on Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution


Post Reply


Please login or register if you wish to leave a comment.

Quick Search

Statistics

3,014 listings in 21 categories, with 1,072,236 clicks. Directory last updated Sep 29, 2017. Welcome vishnureddykal, the newest member.