Yissum - Research Development Company of the Hebrew University

Fast image and video upscaling from self-examples : new high-quality and efficient single-image upscaling technique that extends existing example-based super-resolution frameworks

Posted by Yissum - Research Development Company of the Hebrew UniversityResponsive · Patents for licensing · Israel

Summary of the technology

We presented a new example-based image upscaling method that performs less nearest-patch computations and uses a custom designed filter banks to synthesize the image explicitly. The faster search is based on a local self-similarity observation that we point out in natural images, where edges and other singularities are locally scale invariant. The tests we performed to measure this invariance show that this assumption holds best for small scaling factors.

Comparisons show that the localized search, permitted by the local scale invariance, outperform approximate global searches both in quality and running time. We formulated and designed novel filter banks that allow us to perform such small, non-dyadic, image scalings. These filter banks extend the common dyadic transformations and are designed to model the image upscaling process. With these filters we achieve, using explicit computations, upscaled image which is highly consistent with the input image. Altogether, we propose a fully local high-quality upscaling algorithms that operates in real-time when implemented in a GPU.

Description of the technology

Description of the technology

New image processing algorithm based on example-based super-resolution that results in a high-quality and efficient single-image upscaling technique. Image upsampling exploits local scale-similarity in natural images. When downscaled, the patches (yellow squares) are very similar to their cropped version (red squares).

Specifications

We propose a new high-quality and efficient single-image upscaling technique that extends existing example-based super-resolution frameworks. In our approach we do not rely on an external example database or use the whole input image as a source for example patches. Instead, we follow a local self-similarity assumption on natural images and extract patches from extremely localized regions in the input image. This allows us to reduce considerably the nearest-patch search time without compromising quality in most images. Tests, that we perform and report, show that the local-self similarity assumption holds better for small scaling factors where there are more example patches of greater relevance. We implement these small scalings using dedicated novel non-dyadic filter banks, that we derive based on principles that model the upscaling process. Moreover, the new filters are nearly-biorthogonal and hence produce high-resolution images that are highly consistent with the input image without solving implicit back-projection equations. The local and explicit nature of our algorithm makes it simple, efficient and allows a trivial parallel implementation on a GPU. We demonstrate the new method ability to produce high-quality resolution enhancement, its application to video sequences with no algorithmic modification, and its efficiency to perform real-time enhancement of lowresolution video standard into recent high-definition formats.

Main advantages of its use

  • Algorithm produces high-quality, sharp images
  • Reduces the process search time without compromising quality
  • Simple, efficient, and trivially parallel algorithm enables increase in the resolution of video
  • sequences with no algorithmic modifications and at reasonable running times

Applications

  • Up-scaling video and still images

Related keywords

  • Imaging, Image Processing, Pattern Recognition
  • Description Image/Video Computing
  • Other scanning related (including optical mark sensing and image processing)
  • Image processing
  • video processing
  • video
  • image

About Yissum - Research Development Company of the Hebrew University

Technology Transfer Office from Israel

Yissum Research Development Company of the Hebrew University of Jerusalem Ltd. Founded in 1964 to protect and commercialize the Hebrew University’s intellectual property. Ranked among the top technology transfer companies, Yissum has registered over 8,900 patents covering 2,500 inventions; has licensed out 800 technologies and has spun-off 90 companies. Products that are based on Hebrew University technologies and were commercialized by Yissum generate today over $2 Billion in annual sales.

Send your request

By clicking "Send your request" you are signing up and accepting our Terms of Service and Privacy policy

Technology Offers on Innoget are directly posted and managed by its members as well as evaluation of requests for information. Innoget is the trusted open innovation and science network aimed at directly connect industry needs with professionals online.