Pika Labs has updated its generative video model, Pika 2.0 adding more user control and customizability, the company says. Improvements include better “text alignment,” making it easier to have the AI follow through with intricate prompts. Enhanced motion rendering is said to deliver more “naturalistic movement” and better physics, including greater believability in transformations that tend toward the surreal, which has typically been a challenge for genAI tools. The biggest change may be “Scene Ingredients,” which lets users add their own images when building Pika-generated videos. Continue reading Pika 2.0 Video Generator Adds Character Integration, Objects

Adobe is bringing more Firefly AI features to its popular Photoshop and Illustrator design platforms. The upgrade is a significant step forward for Adobe since the 2023 debut of Firefly, and sees Photoshop finally getting in-app ability to generate AI images, and also a new Generative Shape Fill that is still in beta, allowing designers to quickly add detailed vectors to shapes by entering text prompts directly in the Contextual Taskbar. Improvements to Illustrator include the Dimension Tool, Retype, Style Reference, its own Contextual Taskbar, Retype and two new beta tools, Text to Pattern and Mockup. Continue reading Adobe Adds New Firefly AI Features to Illustrator, Photoshop

Snap Inc. teased a new on-device AI model capable of real-time filter creation in-app using Snapchat. At last week’s Augmented World Expo in Long Beach, California, Snap co-founder and CTO Bobby Murphy explained that the model, which runs on smartphones, can re-render frames on the fly guided by text prompts. Snap’s unnamed prototype model “can instantly bring your imagination to life in AR,” Snap says, explaining “this early prototype makes it possible to type in an idea for a transformation and generate vivid AR experiences in real time.” Continue reading Snapchat Previews Instant AR Filters, GenAI Developer Tools

Nvidia is introducing a new AI feature for its RTX GPUs called RTX Video HDR that upgrades standard video into high dynamic range color space for customers that have an HDR10-compatible monitor running on Windows with HDR enabled. Announced at CES, the technology is now available for download through Nvidia’s January Studio Driver update. “PC game modders now have a powerful new set of tools to use with the release of the Nvidia RTX Remix open beta,” which combines “full ray tracing, Nvidia DLSS and Nvidia Reflex” with “generative AI texture tools so modders can remaster games more efficiently,” according to the company. Continue reading Nvidia GeForce GPUs Using AI to Boost SDR Content to HDR

Apple recently announced advances in artificial intelligence research that could introduce more immersive visual experiences and enable sophisticated AI systems to run on the company’s popular mobile devices. Two new research papers highlight techniques for creating 3D avatars from video content and efficiently deploying large language models on devices challenged by limited memory. The real-time ability to create avatars and 3D scenes from an iPhone camera could bring a range of new possibilities for CE devices in areas such as synthetic media, telepresence, social interaction, virtual try-on and more. Continue reading Apple Unveils New Advances in Artificial Intelligence Research

Apple has announced new 14- and 16-inch iterations of its MacBook Pro laptops, featuring Apple’s next-generation silicon. The M2 Pro and M2 Max chips turn the MacBook Pro into a portable workstation, able to tackle demanding tasks like effects rendering and color grading. Apple is promising up to 22 hours of battery life, the most ever in a Mac. The smaller model starts at $1,999, while entry level for the 16-inch is $2,499. Pre-orders began last week and delivery starts tomorrow. Apple is also releasing an updated Mac mini with M2 ($599) or M2 Pro ($1,299) chips. Continue reading Apple Debuts MacBook Pros with M2 Pro and M2 Max Chips

Intel announced its 13th-gen family of laptop CPUs, including new entry-level chips and its flagship Core i9-13980HX, the high-end of its mobile processor collection (based on Raptor Lake architecture), featuring 24 cores and an impressive boost speed of 5.6GHz. The HX-series includes similar features to Intel’s 12th-gen lineup, such as 32 EUs of onboard graphics capability and support for DDR5 and DDR4, but promises significantly faster speeds to multithreaded performance. When compared to the earlier Core i9-12900HK, Intel claims game performance increases of up to 12 percent and a massive 74–79 performance jump when rendering a scene in Blender. Continue reading CES: Intel Rolls Out 13th-Generation Lineup of Laptop CPUs

Light Field Lab is developing a “naked-eye” holographic technology called SolidLight, which essentially creates high-resolution 3D objects in the real world using light (think the “Star Trek” holodeck or Princess Leia uttering “Help me, Obi-Wan Kenobi” — but better than the actual hologram tech we’ve seen in recent years). “We’re creating a world where content escapes the screen and merges with reality,” claims the Light Field website. SolidLight builds freestanding 3D objects using what the company describes as a “broad-spectrum, complex-amplitude, dense converging wavefront.” Continue reading Light Field Lab Touts ‘Highest Resolution Holographic Display’

The Academy Software Foundation (ASWF), developed by the Academy of Motion Pictures Arts and Sciences and the Linux Foundation to provide a neutral forum for open source software developers, announced that its sixth hosted project is Open Shading Language (OSL), originally developed by Sony Pictures Imageworks. OSL, which was honored with an Academy Scientific and Technical Award in 2017, is now the de facto standard shading language for VFX and animation. ASWF also stated that AMD and DockYard have joined as new members. Continue reading ASWF Announces Its Next Project: Open Shading Language

Apple just submitted an application to the U.S. Patent and Trademark Office for a light field panoramic camera system for next-generation iPhones, iPads and head-mounted displays (HMD). With the camera, the user will be able to capture images (as well as position and orientation information) by holding up the device. Processing the images for relative positions and depth information, the light field panorama will allow a viewer to explore 3D views of the image with 6 degrees of freedom (DOF). Continue reading Apple Files Patent for Light Field Camera System with 6DOF

Transforming 2D objects into 3D ones is a challenge that has defeated numerous artificial intelligence labs, including those at Facebook, Nvidia and startup Threedy.ai. Now, a Microsoft Research team stated it has created the first “scalable” training technique to derive 3D models from 2D data. Their technology can, furthermore, learn to generate better shapes when trained exclusively with 2D images. The Microsoft team took advantage of software that produces images from display data, as featured in industrial renderers. Continue reading Microsoft Develops Scalable 2D-to-3D Conversion Technique

Continue reading Dynamic Branding: Ryff’s Quest for Virtual Product Placement

Light Field Lab raised $28 million in funding to scale its holographic display technology from a prototype into a product. Its technology builds large holographic displays out of smaller building blocks, with the aim of creating holographic images that float in space and are able to be viewed without AR/VR goggles, potentially to be used for live events, holographic TVs and other applications. Chief executive Jon Karafin stated that his company’s goal is to bring holography up to “hundreds of gigapixels of resolution.” German firm Bosch is also developing glasses-free 3D auto displays. Continue reading Light Field Lab Details Future For Holographic Display Tech

Nvidia made a number of compelling announcements at this week’s GPU Technology Conference (GTC 2019) in San Jose, California. The company unveiled its GauGAN AI image creator that uses generative adversarial networks (GANs) to turn sketches into nearly photorealistic images. As part of its cloud pursuits, the company unveiled its latest RTX server configuration that is designed for Hollywood studios and those who want to create visual content quickly (each server pod can support up to 1,280 GPUs). Nvidia also announced partnerships with 3D software makers including Adobe, Autodesk and Unity to integrate Nvidia’s RTX ray-tracing platform. Continue reading Nvidia Demos New Products at Deep Learning & AI Confab

According to a recent note to investors written by analyst Ming-Chi Kuo, who is known for frequently having inside information on Apple’s product plans, Apple could begin mass production of its augmented reality headset by the end of 2019 and unveil it as early as mid-2020 — although he admitted the timeline is optimistic. In May 2018, however, Loup Ventures founder Gene Munster predicted we wouldn’t see the Apple AR headset until late 2021. Kuo stated his belief that Apple’s first AR device will only be a display, with the iPhone performing all the rendering, data connection and GPS. Continue reading Analyst Predicts Apple’s AR Headset to Launch in Mid-2020