Google Patents an AI That Reconstructs 3D Objects From One Photo — and Admits When It's Guessing
Figuring out what a 3D object looks like from a single flat photo is genuinely hard — and most AI systems that…
World models and digital twins: AI that predicts physics, builds 3D scenes, and rehearses reality before acting in it. Early, strange, and worth tracking.
Figuring out what a 3D object looks like from a single flat photo is genuinely hard — and most AI systems that…
Adobe is patenting a way to make 3D mesh construction compatible with machine learning training loops — a longstanding headache in computer…
Before an ad campaign ever reaches a real audience, Adobe wants generative AI to simulate how that audience would likely respond —…
Lidar — the laser-based ranging tech that gives self-driving cars their 3D vision — has a hard distance limit. Nvidia thinks it…
Most autonomous vehicle systems do heavy geometric lifting to convert camera images into a 3D "bird's-eye view" of the world — Qualcomm's…
Matching a photo of an object taken from the front to one taken from the side is surprisingly hard — and Google's…
Nvidia is working on a single AI model that can generate a complete, photorealistic 3D human — face, hands, full body —…
Nvidia is working on a system that can take ordinary, uncontrolled 2D photos — the kind scraped from the internet — and…
Teaching a robot hand to reliably pick up an arbitrary object is one of the hardest unsolved problems in robotics. Nvidia's latest…
Nvidia wants to let neural networks do the heavy lifting of generating high-resolution textures — starting from a cheaper, low-res version and…
Training a 3D digital human model normally requires expensive, controlled capture setups — but Nvidia's new patent describes a way to do…
What if your self-driving car could remember what a street looked like last Tuesday — and use that memory to fill in…
One Big Tech patent every Sunday. Free.