Fast ANN for High-Quality Collaborative Filtering
| dc.contributor.author | Tsai, Yun-Ta | en_US |
| dc.contributor.author | Steinberger, Markus | en_US |
| dc.contributor.author | Pajak, Dawid | en_US |
| dc.contributor.author | Pulli, Kari | en_US |
| dc.contributor.editor | Ingo Wald and Jonathan Ragan-Kelley | en_US |
| dc.date.accessioned | 2015-07-06T15:26:34Z | |
| dc.date.available | 2015-07-06T15:26:34Z | |
| dc.date.issued | 2014 | en_US |
| dc.description.abstract | Collaborative filtering collects similar patches, jointly filters them, and scatters the output back to input patches; each pixel gets a contribution from each patch that overlaps with it, allowing signal reconstruction from highly corrupted data. Exploiting self-similarity, however, requires finding matching image patches, which is an expensive operation. We propose a GPU-friendly approximated-nearest-neighbor algorithm that produces high-quality results for any type of collaborative filter. We evaluate our ANN search against state-of-the-art ANN algorithms in several application domains. Our method is orders of magnitudes faster, yet provides similar or higher-quality results than the previous work. | en_US |
| dc.description.seriesinformation | Eurographics/ ACM SIGGRAPH Symposium on High Performance Graphics | en_US |
| dc.identifier.isbn | 978-3-905674-60-6 | en_US |
| dc.identifier.issn | 2079-8679 | en_US |
| dc.identifier.uri | https://doi.org/10.2312/hpg.20141094 | en_US |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/hpg.20141094 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.subject | I.4.3 [Image Processing and Computer Vision] | en_US |
| dc.subject | Enhancement | en_US |
| dc.subject | Filtering | en_US |
| dc.title | Fast ANN for High-Quality Collaborative Filtering | en_US |
Files
Original bundle
1 - 1 of 1