Image created with Ideogram 3.0. Image prompt: Lower-East-Side street-corner photograph reminiscent of a late-80s album cover: weathered red-brick tenement with exterior fire-escapes, canvas awning shading racks of vintage clothes; above the awning, a hand-painted board reads ‘ARVR SPORTSWEAR’; a hanging blade sign in cursive script reads ‘ARVR Boutique’; an arcade cabinet running an AR/VR demo draws curious kids; warm golden-hour light, subtle 35mm film grain, muted yet punchy color palette, gritty NYC vibe.
Gemini Live camera and screen sharing in @GeminiApp is available on @Android and rolling out to iOS, starting today. https://x.com/Google/status/1924876301573239061
Google is bringing real-time AI camera sharing to Search | The Verge https://www.theverge.com/news/670597/google-search-live-ai-mode-gemini-ios
Gemini 2.5 can now organize vast amounts of multimodal information, reason about everything it sees, and write code to simulate anything. ↓ #GoogleIO https://x.com/GoogleDeepMind/status/1924878250255516126
NVIDIA offers two blueprints for synthetic data generation: ⦿ Isaac GR00T-Mimic: Uses a physics engine to amplify human motion data in simulation. ⦿ GR00T-Dreams (announced yesterday): Fine-tunes a video generation AI model to create new motion videos from a single image. https://x.com/TheHumanoidHub/status/1924538121687073167
Introducing Gemma 3n, our multimodal model built for mobile on-device AI. 🤳 It runs with a smaller memory footprint, cutting down RAM usage by nearly 3x – enabling more complex applications right on your phone, or for livestreaming from the cloud. Now available in early https://x.com/GoogleDeepMind/status/1925916216083779774
Glasses with Android XR are lightweight and designed for all-day wear. They work with your phone so you can be hands-free, stay in the moment with friends and complete your to-do list. https://x.com/Google/status/1924899930109575474
Google Beam: Updates to Project Starline from I/O 2025 https://blog.google/technology/research/project-starline-google-beam-update/
Google Beam: Be there from anywhere with our breakthrough communication technology. https://starline.google/
Exclusive: Google Sees Smart Glasses as the ‘Next Frontier’ for AI. And It’s Not Working Alone – CNET https://www.cnet.com/tech/computing/exclusive-google-sees-xr-smart-glasses-as-the-ultimate-use-for-ai-with-warby-parker-samsung-and-xreal-on-deck/#ftag=CAD590a51e
Google I/O 2025: Gemini on Android XR coming to glasses, headsets https://blog.google/products/android/android-xr-gemini-glasses-headsets/
Wow. No more waiting hours for COLMAP / SfM — you get live 3D Gaussian Splats straight from unposed images, even for massive scenes. Your 3D scene and camera poses are ready right as you finish capturing. Inria team cooked again; code drops end of May. https://x.com/bilawalsidhu/status/1923847046097719730
Apple’s first smart glasses could arrive next year | The Verge https://www.theverge.com/news/673030/apple-ai-smart-glasses-2026-launch-rumor
🚀Introducing Tencent Hunyuan Game, the first industrial-grade AIGC engine for game production. Powered by Hunyuan AI, Hunyuan Game turns ideas into production-ready assets 10X FASTER. ✨ What You Get: 🔹 AI Art Pipeline Streamline inspiration → design → triview in a single, https://x.com/TencentHunyuan/status/1924713242150273424
Our partnership with Samsung is extending to glasses. We’re creating the software and reference hardware, and developers will be able to start building for glasses later this year. https://x.com/Google/status/1924899932949070065
Google is shipping 3D video conferencing tech this year. Project Starline is now Google Beam, with HP being the first OEM to bring it to market. It literally feels like a portal. Having tried this tech while I was at Google for regular meetings — lemme tell you your recall is https://x.com/bilawalsidhu/status/1924889726542348699
Hi Google Beam👋! What started as Project Starline has evolved into a revolutionary 3D video communications platform. The combination of our AI video model and light field display allows you to make eye contact and read subtle cues as if you were face-to-face 🤯 https://x.com/GoogleAI/status/1924880505146847454
What if you could take a 2D video call and make it feel like you’re really there? Google Beam, our new AI-first video communication platform, does just that — using a state-of-the-art AI video model to transform 2D video streams into a realistic 3D experience. #GoogleIO https://x.com/Google/status/1924875328037466302
Really crazy! (open source 3D VR objects) https://x.com/fdaudens/status/1923095695843643848
Google presents LightLab Controlling Light Sources in Images with Diffusion Models https://x.com/_akhaliq/status/1923135902827642901
If they are making translucent windows the new standard, I am going to say unkind things.”” / X https://x.com/ID_AA_Carmack/status/1925736506687131850
EVA: Expressive Virtual Avatars from Multi-view Videos https://vcai.mpi-inf.mpg.de/projects/EVA/
New sota open-source depth estimation: Marigold IID 🌼 > normal maps, depth maps of scenes & faces > get albedo (true color) and BRDF (texture) maps of scenes, they even release a depth-to-3D printer format demo 😮 link to all models and demos on the next one ⤵️ https://x.com/mervenoyann/status/1923318140965990814
Google Android XR Glasses 👓 Live Demo #GoogleIO https://x.com/BenGeskin/status/1924903309065723970
CGS-GAN 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesishttps://fraunhoferhhi.github.io/cgs-gan/
DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations
https://ziqiaopeng.github.io/dualtalk/
