Neural Information Processing Systems http://nips.cc/

However,thisisrarelythecase in real LR images, in contrast to synthetically generated SR datasets. When the assumed downscaling kernel deviates from the true one, the performance of SR methods significantly deteriorates. This gaverise toBlind-SR-namely, SR when the downscaling kernel ("SR-kernel") is unknown.

Last few years have witnessed impressive progress propelled by deep learning methods. However, one critical challenge faced by existing methods is to strike a sweet spot of deep model complexity and resulting SISR quality. This paper addresses this pain point by proposing a linearly-assembled pixel-adaptive regression network (LAPAR), which casts the direct LR to HR mapping learning into a linear coefficient regression task over a dictionary of multiple predefined filter bases.

Deep learning models have grown increasingly complex, with input data sizes scaling accordingly. Despite substantial advances in specialized deep learning hardware, data loading continues to be a major bottleneck that limits training and inference speed. To address this challenge, we propose training models directly on encoded JPEG features, reducing the computational overhead associated with full JPEG decoding and significantly improving data loading efficiency. While prior works have focused on recognition tasks, we investigate the effectiveness of this approach for the restoration task of single-image super-resolution (SISR). We present a lightweight super-resolution pipeline that operates on JPEG discrete cosine transform (DCT) coefficients in the frequency domain. Our pipeline achieves a 2.6x speedup in data loading and a 2.5x speedup in training, while preserving visual quality comparable to standard SISR approaches.

Neural Information Processing Systems http://nips.cc/

Single image super-resolution (SISR) has made a significant breakthrough benefiting from the prevalent rise of deep neural networks and large-scale training samples.