Loss-Specific Training of Random Forests for Super-Resolution

Alexander Grabner, Georg Poier, Michael Opitz, Samuel Schulter, Peter M. Roth

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review


Super-resolution addresses the problem of image upscaling by reconstructing high-resolution output images from low-resolution input images. One successful approach for this problem is based on random forests. However, this approach has a large memory footprint, since complex models are required to achieve high accuracy. To overcome this drawback, we present a novel method for constructing random forests under a global training objective. In this way, we improve the fitting power and reduce the model size. In particular, we combine and extend recent approaches on loss-specific training of random forests. However, in contrast to previous works, we train random forests with globally optimized structure and globally optimized prediction models. We evaluate our proposed method on benchmarks for single image super-resolution. Our method shows significantly reduced model size while achieving competitive accuracy compared to state-of-the art approaches.
Original languageEnglish
Title of host publicationProceedings of the 22nd Computer Vision Winter Workshop
EditorsWalter G. Kropatsch, Ines Janusch, Nicole M. Artner
PublisherTU Wien, Pattern Recongition and Image Processing Group
Number of pages9
ISBN (Electronic)978-3-200-04969-7
Publication statusPublished - 2017


Dive into the research topics of 'Loss-Specific Training of Random Forests for Super-Resolution'. Together they form a unique fingerprint.

Cite this