Computer Vision

NVIDIA and Tel-Aviv University Researchers Propose a Computer Vision Method based on Textual Inversion to Insert New Concepts into Pre-Trained Text-to-Image Models

In the last few years, text-to-image has become one of the most studied topics in the Computer Vision world, resulting in models such as...

Researchers from the Alibaba Group added their newly developed ‘YOLOX-PAI’ into EasyCV, which is an all-in-one Computer Vision Toolbox

One of the most well-known one-stage object detection techniques is YOLOX, which is often utilized in various fields, including automated driving and defect checking....

Deepmind Researchers Introduce ‘Transframer’: A General-Purpose AI Framework For Image Modelling And Computer Vision Tasks Based On Probabilistic Frame Prediction

Transframer is a new general-purpose framework for image modeling and vision applications based on probabilistic frame prediction released by Deepmind researchers. This new paradigm...

Google AI Open-Sources ‘MultiNeRF’: Image Noise Reduction Artificial Intelligence Project Presented at Computer Vision and Graphics Recognition (CVPR) Conference 2022

Software is quickly replacing what was previously a mechanical realm. These recent technological advances are replacing human expertise to some extent as well, especially...

Researchers at the University of Central Florida have developed CitySim, a Video-based Traffic Trajectory Dataset for Advancement in Vehicle-Safety Research

Making an advanced vehicle-safety model or researching it requires a highly accurate annotated dataset. The dataset also must contain certain events that are critical...

To Enable Advanced Research on Artificial Humanoid Control, Microsoft’s Robotics Team is Releasing A Library of Pre-Trained Simulated Humanoid Control Models with Enriched Data...

Simulated humanoids present an intriguing platform for investigating motor intelligence with their ability to mimic the whole spectrum of human motion. An important area...

Researchers from Microsoft Asia and Peking University Proposed NUWA-Infinity, a Model to Generate High-Resolution, Arbitrarily-Sized Images and Videos

In recent years, the generation of images or videos from different types of inputs (text, visual, or multimodal) has gained increased popularity. In this...

Latest Computer Vision Research At Microsoft Explains How This Proposed Method Adapts The Pretrained Language Image Models To Video Recognition

Numerous vision applications heavily rely on video recognition, including autonomous driving, sports video analysis, and microvideo recommendation. A temporal video model is showcased in...

An AI-Powered Smart Camera Achieves Privacy-Preserving Imaging by Only Recording Objects of Interest While Being Blind to Others

Digital cameras have been widely incorporated into our society over the past ten years. They are now extensively employed in facial recognition, mobile phones,...

Researchers at Ludwig-Maximilian University Propose Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models

The development of generative models for text-to-image synthesis has advanced significantly. Recently, these models have had wide success in the application in the field...

Meta AI Releases Implicitron, a Modular Framework for Neural Implicit Representations in PyTorch3D

Exciting new opportunities for augmented reality experiences are being made possible by the quick advancements in neural implicit representation. Without much training data or...

Researchers at Apple Develop Texturify: A GAN-based Approach for Generating Textures on 3D Shape Surfaces

The development of 3D content for visual consumption in movies, video games, and mixed reality environments is one of many application areas where it...

Recent articles