Computer Vision

Deepmind Researchers Propose A Machine Learning-Based Framework For Doing Research On Hour-Long Films Using The Same Technology That Can Presently Analyze Second-Long Videos

Raw movies are massive and must be compressed before being saved on a disc; once loaded, they are decompressed and placed in device memory...

Researchers from MIT and Microsoft Propose a Practical and Robust Video Conferencing Method Called Gemino That Uses Neural Compression System

We all saw the importance of good-quality video conferencing tools during COVID lockdowns. Education, entertainment, work meetings, and family visits became video conferences, and...

Meet ‘DreamFusion,’ An Effective AI Technique That Uses Machine Learning To Synthesize 3D Models From Text Prompts

By prompting a text-to-image model we can generate images of a wide variety of objects. With clever prompting, it’s also possible to synthesize different...

Latest Robotics Research Releases ‘Hora’: A Single Policy Capable of Rotating Diverse Objects With a Dexterous Robot Hand

In this article, UC Berkeley and Meta researchers demonstrate how an adaptive controller can be trained to rotate various objects over the z-axis using...

CMU Researchers Introduce a Content-based Search Engine for Modelverse, a Model-Sharing Platform that Contains a Diverse Set of Deep Generative Models

The goal of the content-based model search is introduced, which tries to locate the most relevant deep image generative models that fulfill a user's...

Understanding the Role of Artificial Intelligence (AI) in Building Smart Cities and Top Startups Working on it

A report by McKinsey Global Institute finds that 'Smart Cities' can improve essential quality of life indicators by 10-30 % - such as shorter...

Researchers From UC Berkeley Develop NerfAcc, A PyTorch Nerf Acceleration Toolbox For Both Training And Inference

Neural Radiance Fields (NeRFs) is a revolutionary approach for 3D representation that uses a multi-layer perceptron to describe the geometry and view-dependent appearance of...

Harvard Researchers Propose a Self-Supervised Deep Learning Algorithm for Fast and Scalable Search of Whole-Slide Images

The necessity for accurate and economical gigapixel image analysis has risen as whole-slide imaging has become more widely used. Deep learning is at the...

Latest Computer Vision Research Proposes Lumos for Relighting Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation

If you have ever worked with photo editing, then you probably know how cumbersome it can be to adjust the lighting of a portrait...

Meet Phenaki: A Machine Learning-Based Model For Generating Videos From Text Prompts And Uses C-ViViT As Video Encoder

Text-to-image generation is a hot topic in the AI domain, mainly thanks to the open-source release of stable-diffusion. Do you want to see an...

Researchers at Apple Develop ‘RoomPlan’: An API for Representing Rooms in a 3D Parametric View

Machine learning (ML) research on 3D scene interpretation has been ongoing for over a decade. For the developer and computer vision communities, a new...

Google AI Introduces Frame Interpolation for Large Motion (FILM): A New Neural Network Architecture To Create High-Quality Slow-Motion Videos From Near-Duplicate Photos

Many studies are increasingly focusing on frame interpolation, which synthesizes intermediate pictures between a pair of input frames. The refresh rate can be increased,...

Recent articles