Nvidia debuted a deep learning method that can edit or reconstruct an image that is missing pixels or has holes via a process called “image inpainting.” The model can handle holes of “any shape, size, location or distance from image borders,” and could be integrated in photo editing software to remove undesirable imagery and replace it with a realistic digital image – instantly and with great accuracy. Previous AI-based approaches focused on rectangular regions in the image’s center and required post processing. Continue reading Nvidia’s New AI Method Can Reconstruct an Image in Seconds

Snapchat launched its Lens Studio AR developer tool for desktop that enables users to build augmented reality experiences for the platform. Anyone can now create World Lenses for adding interactive 3D objects to photos and video content. “But brands, news publishers and developers will have to promote their own Lenses by marketing their QR Snapcodes that users scan to unlock an AR effect for 24 hours,” reports TechCrunch. “That’s because Snapchat won’t display these Community Lenses in its camera unless businesses pay a partnered creative agency to build them a special effect and then buy Sponsored Lens ads from Snap.” Continue reading Snapchat Users Can Now Create World Lenses with AR Tool

Adobe’s research team is working on a visual effects tool, codenamed Cloak, for easy and economical removal of rigs, power lines and other unwanted parts of an image. The tool is similar to Photoshop’s content-aware fill feature that lets the user select and delete unwanted elements in the image, with “intelligent” software filling in the missing background behind them. Doing the same thing with video, however, is more challenging, which is why Cloak is still in an experimental stage, with no release date slated. Continue reading Adobe Experiments With Easy Object Removal Tool for Video

Startup camera company Light just debuted the L16, which weighs less than a pound, has a form factor small enough to fit in a back pocket and replaces one large lens with 16 smaller lenses and sensors that produce a 52-megapixel image. That image compares to the typical smartphone’s 12-megapixel image or 30-megapixel image from a DSLR camera. The L16 — intended for photography, not video, and priced at $1,950 — also offers an adjustable optical zoom that allows the user to change the level of background blur and focus. Continue reading Unique Compact Still Camera Captures 52-Megapixel Images

The traditional bluescreen/greenscreen method of extracting foreground content from the background for film and video production may be on its way out. That’s due to research that Adobe is doing in collaboration with the Beckman Institute for Advanced Science and Technology, to develop a new system that relies on deep convolutional neural networks. A recent paper, “Deep Image Matting,” reports that the new method uses a dataset of 49,300 training images to teach the algorithm how to distinguish and eliminate backgrounds. Continue reading Adobe’s AI-Enabled System Could Replace Greenscreen Tech

FaceApp relies on neural networks to paste a smile on a person’s photo or change his gender or age. The iOS app doesn’t always work reliably; if the person’s face is large, has a beard or isn’t looking straight at the camera, for example, the results can be unconvincing. Switching genders can produce convincing results, but can only be accessed in “collage” mode, for a very small image. But FaceApp, similar to the Prisma app that uses artificial intelligence to make selfies look like famous paintings, proves that AI is making it easier to manipulate photographs. Continue reading FaceApp Uses Neural Networks to Alter Age, Gender in Photos

Adobe Research and Princeton University are collaborating on software that acts like Photoshop for audio, including the ability to add words not found in the original audio file. Adobe developer Zeyu Jin, who spoke at the Adobe MAX conference, described the would-be product, codenamed Project VoCo, as a “sneak peak.” Project VoCo is intended to be an audio editing application, with more typical speech editing and noise cancellation features, but the Photoshop-like tool also raises potential ethical issues regarding the use of doctored audio clips.

Continue reading Adobe Project VoCo Audio Editor Offers Photoshop-Like Tools

Among Adobe’s updates to Creative Cloud applications is the debut of Project Felix, a 2D/3D compositing tool that allows the user to easily combine 2D and 3D objects and create a photorealistic scene. Photoshop CC now offers a universal search tool for searching Adobe Stock, and other workflow-related features. After Effects has a new 3D rendering engine that’s twenty times faster than before, and Premiere now offers better support for VR content and Character Animator. Adobe also previewed the Project Nimbus photo editor. Continue reading Adobe Introduces Extensive Updates for Creative Cloud Apps

Linux production environments can now leverage Nvidia’s recently introduced GRID technology to power VMware’s Horizon 6 for Linux and provide visual effects and animation artists anywhere, on any device, with virtual Linux workstations running their familiar high-end applications. Nvidia’s VP of Enterprise Marketing Greg Estes showed a virtual workstation running simulations in Maya on the SIGGRAPH floor in Los Angeles with the application, processors and Nvidia’s GRID and CUDA technologies installed in a data center hundreds of miles away in Northern California. Continue reading Linux to Go: Nvidia GRID Delivers Virtualization, Performance

With the recent growth in citizen journalism via the Internet, questions have arisen regarding the authenticity of photographs, and whether there are ways to verify if an image is accurate or not. The rise of Photoshop and other digital tools has made it easy for people to edit images prior to sharing them on Facebook or Twitter. However, a computer science professor at Dartmouth College has developed a free online image verification service that quickly confirms whether an image is authentic or not. Continue reading Professor Develops Free DIY Online Image Verification Service

Getty Images along with AP, AFP, Reuters, and EPA wire agencies have set up state-of-the-art fiber optic networks to deliver Olympic images almost instantaneously. Getty can deliver photographs from the Winter Olympics in Sochi directly to publications within 180 seconds thanks to 20 kilometers of cable and a 100Mbps network. The process of preparing an image for delivery in record speed involves a team of Photoshop experts, captioning specialists, and editors. Continue reading Getty Images Delivers Winter Olympic Photos in Record Speeds

DAQRI, an augmented reality developer, is creating software and augmented reality apps, combined with EEG monitoring devices and Google Glass, to bring mental control over physical and virtual environments. The company has created several augmented realities for marketing, entertainment, commercial and educational uses. The company’s efforts to add EEG sensors bring new ways to control devices, what is connected to them, and the environments they create. Continue reading Bringing Mental Concentration Control to Augmented Reality