Deep Sampling Networks
This addresses image processing bottlenecks for applications like super-resolution and compression, though it appears incremental as it builds on CNN-based methods.
The paper tackles the problem of image up-sampling and down-sampling by introducing a deep sampling network (DSN) that eliminates reliance on traditional interpolations, achieving new state-of-the-art performance in image super-resolution and improving image compression compatibility.
Deep convolutional neural networks achieve excellent image up-sampling performance. However, CNN-based methods tend to restore high-resolution results highly depending on traditional interpolations (e.g. bicubic). In this paper, we present a deep sampling network (DSN) for down-sampling and up-sampling without any cheap interpolation. First, the down-sampling subnetwork is trained without supervision, thereby preserving more information and producing better visual effects in the low-resolution image. Second, the up-sampling subnetwork learns a sub-pixel residual with dense connections to accelerate convergence and improve performance. DSN's down-sampling subnetwork can be used to generate photo-realistic low-resolution images and replace traditional down-sampling method in image processing. With the powerful down-sampling process, the co-training DSN set a new state-of-the-art performance for image super-resolution. Moreover, DSN is compatible with existing image codecs to improve image compression.