Image created with gemini-3.1-flash-image-preview with claude-opus-4.7. Image prompt: Using the provided reference images, keep the authentic Sonoran Desert trail setting, lighting, and the brown-post ranger sign construction with bold typography, but change the sign header to ‘AR/VR’ with fictional entries like ‘→ Headset Hollow 1.2’, ‘← Overlay Overlook 2.8’, ‘→ Passthrough Peak 4.5’ and a small lens-shaped emblem replacing the medallion, and add a hiker in the mid-ground wearing translucent mixed-reality glasses with faint ghostly waypoint icons and a thin contour-line overlay hovering subtly above the trail ahead, all photorealistic and naturally integrated into the desert scene.
Google DeepMind partners with EVE Online for AI model testing – Ars Technica
https://arstechnica.com/gaming/2026/05/google-deepmind-partners-with-eve-online-for-ai-model-testing/
Google is testing new Omni model for video generation
https://www.testingcatalog.com/google-is-testing-new-omni-model-for-video-generation-ahead-of-i-o/
Studio Behind EVE Online Goes Independent, Rebrands as Fenris Creations, Enters Research Partnership with Google DeepMind – Fenris Creations
https://www.ccpgames.com/news/2026/studio-behind-eve-online-goes-independent-rebrands-as-fenris-creations-enters-research-partnership-with-google-deepmind
Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation”” TL;DR: combines LLM planning with vision-guided refinement to generate physically plausible and coherent 3D scenes from text
https://x.com/Almorgand/status/2051320217674870795
Okay the geospatial nerd in me needs to fly Air France just so I can enjoy these multi camera views
https://x.com/bilawalsidhu/status/2050378363018027091
Woah! Ouster has made the world’s first native color LiDAR sensor and it looks bloody glorious. Why debate cameras vs lasers when you can get the best of both worlds — no obtuse fusion with RGB cameras required.
https://x.com/bilawalsidhu/status/2051432406876377249
World’s first native color LiDAR sensor. I want one of these puppies.
https://x.com/bilawalsidhu/status/2051657980181934298
STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer”” TL;DR: reframes 3D reconstruction as a causal transformer problem, enabling scalable streaming reconstruction for long and dynamic sequences
https://x.com/Almorgand/status/2049887765110587490
The next generation of street view will be wildly immersive.
https://x.com/bilawalsidhu/status/2050045605997592709
Whether you love or hate AI, we can all agree the slot machine nature of generative models sucks. Creators need control — and perhaps the best way to get it is with 3d tools. But the first time you open blender, it’s overwhelming. Like staring at a 747 cockpit with a dizzying
https://x.com/bilawalsidhu/status/2050688514245980184
Leave a Reply