Papers with Code · CC BY-SA 4.0
Image Super-Resolution
Image Super-Resolution is a machine learning task where the goal is to increase the resolution of an image, often by a factor of 4x or more, while maintaining its content and details as much as possible. The end result is a high-resolution version of the original image. This task can be used for various applications such as improving image quality, enhancing visual detail, and increasing the accuracy of computer vision algorithms.
데이터셋
84개Set5 - 8x upscalingSyntheticBurstSet14 - 8x upscalingVggFace2 - 8x upscalingWebFace - 8x upscalingBSD100 - 8x upscalingImageNetCelebAManga109 - 8x upscalingUrban100 - 8x upscalingCelebA-HQ 128x128DIV8K val - 16x upscalingGeneral100 - 4x upscalingPIRM-test2x upscaling3x upscaling4x upscalingB100 - 2x upscalingB100 - 3x upscalingB100 - 4x upscalingBSDS100 - 2x upscalingCUFED5 - 4x upscalingDIV2K val - 8x upscalingGeneral100 - 8x upscalingSen2venus - 2x upscalingSun80 - 4x upscalingBSD100 - 16x upscalingBSD200 - 2x upscalingBSDS100 - 4x upscalingBSDS100 - 8x upscaling