We introduce Sana, a text-to-image framework that can efficiently generate images up to 4096 × 4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image ...

The capability to create high-resolution, photorealistic images from text has transformative potential across fields like content creation, gaming, synthetic data generation, and digital avatar design ...

A research team led by Prof. XIE Chengjun and ZHANG Jie from the Hefei Institutes of Physical Science of the Chinese Academy ...

"Many insurance companies are still relying on aerial data collection methods from the 1950s to assess 2024's climate risks." ...

Such high-resolution aerial images can help those responding to climate-related natural disasters – but they also raise privacy concerns. “This is the first time ever that nationwide aerial ...

Near Space Labs, a US-based startup, aims to use stratospheric robots to monitor and assess disaster-prone areas in the US.

From being rudimentary necessity, charging cords have developed into vital resources for navigating the contemporary digital ...

Despite community and investor enthusiasm around visual generative AI, the output from such systems is not always ready for ...

We aim at accelerating super-resolution (SR) networks on large images (2K-8K). The large images are usually decomposed into small sub-images in practical usages. Based on this processing, we found ...

China launches the world's first self-navigating satellites, equipped with advanced AI and SAR technology for autonomous ...

While NASA's NEOWISE telescope ended its journey through space on Nov. 1, 2024, the team at IPAC, a science center at Caltech, was working on one further gift from the prolific mission. The final ...

This article explores the role video borescopes play in nuclear plant inspections, emphasizing the value they bring in terms ...