Computer Vision

As the company behind Stable Diffusion, Stability AI is best recognized for developing some of the most well-known state-of-the-art AI models for a variety of applications, including language, vision, audio, 3D modeling, etc. The $1 billion...
GPT-4 has been released, and it is already in the headlines. It is the technology behind the popular ChatGPT developed by OpenAI which can generate textual information and imitate humans in question answering. After the success...

Mimicking is the Way: Innovative AI Model Lets Robots Learn Tasks by Watching Human Videos

Robots are incredible. They have already revolutionized the way we live and work, and they still have the potential to do it again. They...

A New Artificial Intelligence (AI) Study Proposes A 3D-Aware Blending Technique With Generative NeRFs

Image blending is a primary method in computer vision, one of the most known branches in the artificial intelligence component. The goal is to...

A New AI Research Proposes VoxFormer: A Transformer-Based 3D Semantic Scene Completion Framework

Understanding a holistic 3D picture is a significant challenge for autonomous vehicles (AV) to perceive. It directly influences later activities like planning and map...

A New Artificial Intelligence (AI) Study From CMU and Meta Proposes a Framework for Efficient Neural Relighting of Articulated Hand Models

Neural rendering is a cutting-edge technology that uses artificial intelligence and deep learning to create photorealistic images and animations. Unlike traditional rendering techniques that...

Bringing the Power of NeRF to Your Home: This AI Model Makes Generating Renders Memory Efficient

Do you remember those advanced computers in sci-fi movies where everything is in 3D, you can move what you see around with your fingers,...

Computer Vision Meets 🫠 Reinforcement Learning: This AI Research Shows that Reward Optimization is a Viable Option to Optimize a Variety of Computer Vision...

Not how effectively the model maximizes the training goal, but rather how well the predictions are matched with the task risk, i.e., the model's...

Researchers From Stanford Introduce Disruptive Attention Consistency Method to Catapult Computer Vision Performance with Limited Datasets

In many real-world computer vision problems, such as healthcare, labeled training data can be scarce, leading to the development of machine learning models that...

Researchers From UNSW Sydney Proposes A Deep Learning Algorithm That Produces High-Resolution Modeled Images From Lower-Resolution Micro X-ray Computerized Tomography (CT)

Researchers have turned away from fossil fuels in favor of clean and renewable energy sources in response to the significant change in climate over...

Meet pix2pix-zero: A Diffusion-Based Image-to-Image Translation Method that Allows Users to Specify the Edit Direction on-the-fly (e.g., Cat → Dog)

Over the past few years, many advancements have been made in the field of Artificial intelligence, and one such development is text-to-image generation models....

CMU Researchers Create An AI Model That Can Detect The Pose of Multiple Humans In A Room Using Only The Signals From WiFi

Significant advancement in 2D and 3D human posture estimation using RGB cameras, LiDAR, and radars has been made possible by improvements in computer vision...

A New Artificial Intelligence (AI) Research From The University of Maryland Propose A Shape-Aware Text-Driven Layered Video Editing Tool

Video editing, the process of manipulating and rearranging video clips to meet desired objectives, has been revolutionized by the integration of artificial intelligence (AI)...

This AI Model Called SeaFormer Brings Vision Transformers to Mobile Devices

The introduction of the vision transformer and its massive success in the object detection task has attracted a lot of attention toward transformers in...

Recent articles

Be the first to know the latest AI research breakthroughs.

X