Computer Vision

This AI Research Unveils Photo-SLAM: Elevating Real-Time Photorealistic Mapping on Portable Devices

In computer vision and robotics, simultaneous localization and mapping (SLAM) with cameras is a key topic that aims to allow autonomous systems to navigate...

CMU Researchers Unveil Diffusion-TTA: Elevating Discriminative AI Models with Generative Feedback for Unparalleled Test-Time Adaptation

Diffusion models are used for generating high-quality samples from complex data distributions. Discriminative diffusion models aim to leverage the principles of diffusion models for...

Deep Learning in Human Activity Recognition: This AI Research Introduces an Adaptive Approach with Raspberry Pi and LSTM for Enhanced, Location-Independent Accuracy

Human Activity Recognition (HAR) is a field of study that focuses on developing methods and techniques to automatically identify and classify human activities based...

Meet DreamSync: A New Artificial Intelligence Framework to Improve Text-to-Image (T2I) Synthesis with Feedback from Image Understanding Models

Researchers from the University of Southern California, the University of Washington, Bar-Ilan University, and Google Research introduced DreamSync, which addresses the problem of enhancing...

Google AI and Tel Aviv University Researchers Present an Artificial Intelligence Framework Uniting a Text-to-Image Diffusion Model with Specialized Lens Geometry for Image Rendering

Recent progress in image generation leverages large-scale diffusion models trained on paired text and image data, incorporating diverse conditioning approaches for enhanced visual control....

Google DeepMind Research Introduced SODA: A Self-Supervised Diffusion Model Designed for Representation Learning

Google DeepMind's researchers have developed SODA, an AI model that addresses the problem of encoding images into efficient latent representations. With SODA, seamless transitions...

Stability AI Introduces Adversarial Diffusion Distillation (ADD): The Groundbreaking Method for High-Fidelity, Real-Time Image Synthesis in Minimal Steps

In generative modeling, diffusion models (DMs) have assumed a pivotal role, facilitating recent progress in producing high-quality picture and video synthesis. Scalability and iterativeness...

Researchers from Peking University and Microsoft Introduce COLE: An Effective Hierarchical Generation Framework that can Convert a Simple Intention Prompt into a High-Quality Graphic...

Natural picture production is now on par with professional photography, thanks to a notable recent improvement in quality. This advancement is attributable to creating...

Meet SceneTex: A Novel AI Method for High-Quality, Style-Consistent Texture Generation in Indoor Scenes

High-quality 3D content synthesis is a crucial yet challenging problem for many applications, such as autonomous driving, robotic simulation, gaming, filmmaking, and future VR/AR...

Breaking the Boundaries in 3D Scene Representation: How a New AI Technique is Changing the Game with Faster, More Efficient Rendering and Reduced Storage...

NeRF represents scenes as continuous 3D volumes. Instead of discrete 3D meshes or point clouds, it defines a function that calculates color and density...

This AI Paper from Northeastern University and MIT Develop Interpretable Concept Sliders for Enhanced Image Generation Control in Diffusion Models

Finer control over the visual characteristics and notions represented in a produced picture is typically required by artistic users of text-to-image diffusion models, which...

UC Berkeley Researchers Develop ALIA: A Breakthrough in Automated Language-Guided Image Augmentation for Fine-Grained Classification Tasks

Fine-grained image classification is a computer vision task aiming to classify images into subcategories within a larger category. It involves the intricate identification of...

Recent articles