U-Net

14 Posts

Diffusion Transformed: A new class of diffusion models based on the transformer architecture
U-Net

Diffusion Transformed: A new class of diffusion models based on the transformer architecture

A tweak to diffusion models, which are responsible for most of the recent excitement about AI-generated images, enables them to produce more realistic output.
Stratego Master: DeepNash, the RL system that plays Stratego like a master
U-Net

Stratego Master: DeepNash, the RL system that plays Stratego like a master

Reinforcement learning agents have mastered games like Go that provide complete information about the state of the game to players. They’ve also excelled at Texas Hold ’Em poker, which provides incomplete information, as few cards are revealed.
Like Diffusion but Faster: The Paella model for fast image generation, explained
U-Net

Like Diffusion but Faster: The Paella model for fast image generation, explained

The ability to generate realistic images without waiting would unlock applications from engineering to entertainment and beyond. New work takes a step in that direction.
The Dark Side of the Moon — Lit Up! AI Illuminates Dark Regions of the Moon
U-Net

The Dark Side of the Moon — Lit Up! AI Illuminates Dark Regions of the Moon

Neural networks are making it possible to view parts of the Moon that are perpetually shrouded by darkness. Researchers devised a method called Hyper-effective Noise Removal U-net Software (HORUS) to remove noise from images of the Moon’s south pole.
Panda on a swing
U-Net

Text to Video Without Text-Video Training Data: Make-A-Video, an AI System from Meta, Generates Video from Text

Text-to-image generators like DALL·E 2, Midjourney, and Stable Diffusion are winning art contests and worrying artists. A new approach brings the magic of text-to-image generation to video.
Fake face diagram - FaceSynthetics
U-Net

Fake Faces Are Good Training Data: Synthetic data improves face recognition performance.

Collecting and annotating a dataset of facial portraits is a big job. New research shows that synthetic data can work just as well.
Images generated by a network designed to visualize what goes on in peoples’ brains while they watch Doctor Who
U-Net

Deciphering The Brain’s Visual Signals: AI uses brain activity to create images.

What’s creepier than images from the sci-fi TV series Doctor Who? Images generated by a network designed to visualize what goes on in peoples’ brains while they watch Doctor Who.
Examples of CT scans with different contrasts
U-Net

More Data for Medical AI: AI recognizes medical scans without iodine dye.

Convolutional neural networks are good at recognizing disease symptoms in medical scans of patients who were injected with iodine-based dye, that makes their organs more visible. But some patients can’t take the dye. Now synthetic scans from a GAN are helping CNNs learn to analyze undyed images.
Example of Occupancy Anticipation, a navigation system that predicts unseen obstacles, working
U-Net

Guess What Happens Next: Research teaches robots to predict unseen obstacles.

New research teaches robots to anticipate what’s coming rather than focusing on what’s right in front of them. Researchers developed Occupancy Anticipation (OA), a navigation system that predicts unseen obstacles in addition to observing those in its field of view.
Method overview of model that makes a person on video appear to speak words from a separate audio recording
U-Net

Guest Speaker: Deepfake method syncs up mouth movements with words.

Deepfake videos in which one person appears to speak another’s words have appeared in entertainment, advertising, and politics. New research ups the ante for an application that enables new forms of both creative expression and
Fragment of a video explaining a model that extracts landmarks on the fly from radar scans
U-Net

Locating Landmarks on the Fly: AI model identifies stationary objects from radar scans.

Directions such as “turn left at the big tree, go three blocks, and stop at the big red house on your left” can get you to your destination because they refer to stationary landmarks. New research enables self-driving cars to identify such stable indicators on their own.
Results of a technique that interprets reflected light to reveal objects outside the line of sight
U-Net

Periscope Vision: Researchers used deep learning to see around corners.

Wouldn’t it be great to see around corners? Deep learning researchers are working on it. Researchers developed deep-inverse correlography, a technique that interprets reflected light to reveal objects outside the line of sight.
Anonymous Faces
U-Net

Anonymous Faces

A number of countries restrict commercial use of personal data without consent unless they’re fully anonymized. A new paper proposes a way to anonymize images of faces, purportedly without degrading their usefulness in applications that rely on face recognition.
Neural Point Based Graphics technique producing a realistic image
U-Net

Points Paint the Picture

Creating a virtual representation of a scene using traditional polygons and texture maps involves several complex operations, and even neural-network approaches have required manual preprocessing. Researchers propose a new deep-learning pipeline that visualizes scenes with far less fuss.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox