オープンデータとプログラミング

Adobe は、深い学習 ソフトウェアで複雑な写真の排気切替器を改善したいです。|Adobe wants to improve complex photo cutouts with deep learning software

オープンデータ関連のニュースです。

http://www.digitaltrends.com/photography/adobe-research-deep-matte-learning/

日本語

TranslateApiException: Cannot find an active Azure Market Place Translator Subscription associated with the request credentials. : ID=0151.V2_Json.Translate.3B04E02E
続きを読む…

English

Clipping out objects from photos and videos is often a time-consuming process — but Adobe is looking for new ways to change that with deep learning software. Published earlier this month, the research for Deep Image Mapping by Adobe, the Beckman Institute for Advanced Science and Technology and the University of Illinois at Urbana-Champaign aims to improve on software-based clipping solutions. Researchers have developed a number of different artificially intelligent programs to automatically subtract a background from an image, but most are based on colors. When presented with an image with similar colors such as the greens in a landscape photo, those programs tend to fail, Adobe says.
Read more…

Comments are closed.