Qualitative results are presented on several tasks where paired training data does not exist, including collection style transfer, object transfiguration, season transfer, photo enhancement, etc.
Source : Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
With “RAISR: Rapid and Accurate Image Super-Resolution”, we introduce a technique that incorporates machine learning in order to produce high-quality versions of low-resolution images. RAISR produces results that are comparable to or better than the currently available super-resolution methods, and does so roughly 10 to 100 times faster, allowing it to be run on a typical mobile device in real-time. Furthermore, our technique is able to avoid recreating the aliasing artifacts that may exist in the lower res
Source : Research Blog: Enhance! RAISR Sharp Images with Machine Learning
Algorithms are already looking through the viewfinder alongside with you: they adjust settings, scan faces and take a photo when you smile. What if your grin wasn’t the only thing they cared about?
« Ah ! Fitness Selfies »
Source : Camera Restricta — Philipp Schmitt
via A. Oricheta.
Upon first glance, this photo appears to show presidential candidate Hillary Clinton being ignored by a crowd of people pointing their phones at something out of view to the left. But nope… what you see is selfie culture.
Source : This Hillary Clinton Photo is a Snapshot of the Selfie Generation
Mapping historical photos from the NYPL
Source : OldNYC: Mapping Historical Photographs of New York City
Photographers’ Identities Catalog (PIC) is an experimental interface to a collection of biographical data describing photographers, studios, manufacturers, and others involved in the production of photographic images. Consisting of names, nationalities, dates, locations and more, PIC is a vast and growing resource for the historian, student, genealogist, or any lover of photography’s history. The information has been culled from trusted biographical dictionaries, catalogs and databases, and from extensive original research by NYPL Photography Collection staff.
This project is an attempt to use modern deep learning techniques to automatically colorize black and white photos.
Source : Automatic Colorization
Reuters, the news and photography agency, has issued an outright ban on photographs captured and submitted in RAW format. Instead, freelance contributors must now only submit photos that were processed and stored as JPEG inside the camera.
Source : Reuters bans submission of RAW photos: “Our photos must reflect reality.” | Ars Technica
Photography in a whole new light. Introducing the Light L16 Camera.
Source : Light
© 2023 no-Flux
Theme by Anders Noren — Up ↑
