Google’s updated Veo model can make vertical videos from reference images with 4K upscaling

Google’s Veo video AI made stunning leaps in fidelity in 2025, and Google isn’t stopping in 2026. The company has announced an update for Veo 3.1 that adds new capabilities when you provide the model ...

3D map of Easter Island takes you places visitors aren’t allowed

Nestled in the South Pacific Ocean, some 6,000 people live on the most isolated, inhabited island in the world: Rapa Nui.
Digital Camera World

Researchers hacked a weird Franken-lens to a Canon EOS R10 to take photos with everything in focus – without computational photography

Four lenses and a Spatial Light Modulator allow each pixel to have a different focal length in research from Carnegie Mellon ...
GitHub

[ICCV 2025] CityGS-X : A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstruction

We tested CityGS-X on a server configured with Ubuntu 18.04, cuda 11.6 and gcc 9.4.0. Other similar configurations should also work, but we have not verified each one individually. When training on a ...
Anchorage Daily News

What’s inside a volcano? Scientists obtain first 3D images of Mexico’s Popocatépetl

After five years of climbing the volcano and analyzing seismic data with artificial intelligence, scientists now know where ...
IEEE

Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completion

Abstract: Depth completion is a pivotal challenge in computer vision, aiming at reconstructing the dense depth map from a sparse one, typically with a paired RGB image. Existing learning-based models ...
digitalcameraworld

Researchers let an AI generate thousands of images without human input. The lack of originality was “sobering for computational creativity”, with images only falling into ...

A group of researchers had an AI write a prompt and an AI generate an image, and found only 12 common motifs repeated in thousands of images When you purchase through links on our site, we may earn an ...
eLife

Human EEG and artificial neural networks reveal disentangled representations and processing timelines of object real-world size and depth in natural images

Remarkably, human brains have the ability to accurately perceive and process the real-world size of objects, despite vast differences in distance and perspective. While previous studies have delved ...
IEEE

A Survey on Self-Supervised Monocular Depth Estimation Based on Deep Neural Networks

Abstract: Monocular depth estimation aims to predict the corresponding scene depth map to an input image, which has wide application prospects in various fields, such as robot navigation, autonomous ...
CNET

ChatGPT's New Image Generator Is Better, but It's Still No Nano Banana

ChatGPT Images is a big step forward for OpenAI. Here's how the new model fared against the old one and competitors like Google. Katelyn is a writer with CNET covering artificial intelligence, ...