Computer Vision

Fox (benchmark)

Fox is an evaluation suite for fine-grained, multi-page document understanding by large vision-language models. It was released in May 2024 alongside a model...

AI BenchmarksMultimodal AI

Frechet Inception Distance

The Frechet Inception Distance (FID) is the standard metric for measuring the quality of images produced by generative models: it computes the Frechet distance...

AI BenchmarksGenerative AI

GAIA-2 (Wayve)

GAIA-2 (Generative AI for Autonomy 2) is a controllable, multi-camera generative world model for autonomous driving, announced by the British self-driving...

AI ModelsAutonomous Vehicles

GAIA-3 (Wayve)

GAIA-3 is a 15-billion-parameter generative world model for autonomous driving released by Wayve on 2 December 2025, the third generation in the company's GAIA...

AI ModelsAutonomous Vehicles

Gaussian Splatting

Gaussian splatting is a method for real-time radiance field rendering that represents a 3D scene as a collection of millions of anisotropic 3D Gaussian...

Deep Learning

GenAI-Bench

GenAI-Bench is an AI benchmark for evaluating compositional text-to-image and text-to-video generation, introduced in 2024 by researchers from Carnegie Mellon...

AI Benchmarks

GenEval

GenEval is an object-focused benchmark for evaluating how well text-to-image models follow the content of a prompt. Instead of scoring overall image quality,...

AI BenchmarksImage Generation

GoogLeNet (Inception v1)

GoogLeNet, also known as Inception v1, is a 22-layer deep convolutional neural network introduced by Google researchers in 2014 that won the classification...

AI HistoryAI Models

Grad-CAM

Grad-CAM (Gradient-weighted Class Activation Mapping) is a technique for producing visual explanations from convolutional neural network (CNN) models by using...

Deep LearningInterpretability

Grok Imagine

Grok Imagine is a generative media product from xAI, the company founded by Elon Musk. It produces still images, short videos with synchronized audio, and...

AI CompaniesAI Models

Hiera

Hiera is a hierarchical vision transformer from Meta AI (FAIR), introduced in the paper "Hiera: A Hierarchical Vision Transformer without the...

Meta AITransformer Models

Hikvision

Hangzhou Hikvision Digital Technology Co., Ltd. (Chinese: 杭州海康威视数字技术股份有限公司), commonly known as Hikvision, is a Chinese state-controlled multinational...

AI CompaniesChinese AI

HunyuanWorld 1.0

HunyuanWorld 1.0 is an open model from Tencent that generates explorable 3D worlds from a text prompt or a single image. The Hunyuan team released it on July...

Chinese AIGenerative AI

I-JEPA

I-JEPA (Image-based Joint-Embedding Predictive Architecture) is a self-supervised learning method for computer vision developed by Meta AI. It was introduced...

Machine LearningMeta AI

Ideogram 3.0

Ideogram 3.0 is a text-to-image generation model released by Ideogram on March 26, 2025. It is best known for rendering legible, correctly spelled text inside...

AI ModelsGenerative AI

Image Classification Models

Image classification models are machine learning systems that assign one or more category labels to a whole input image, the task that drove the modern wave of...

AI Models

Image Recognition

Image recognition is the field of artificial intelligence and computer vision that enables machines to identify, classify, and interpret the objects, patterns,...

Deep LearningMachine Learning

Image segmentation

Image segmentation is the computer vision task of partitioning a digital image into multiple regions by assigning every pixel a label, producing a pixel-level...

Deep LearningMachine Learning

Image-to-Image Models

Image-to-image models (often shortened to img2img) are machine learning systems that take an input image and output a transformed version of it. The...

AI Models

ImageNet

ImageNet is a large-scale image database of more than 14 million hand-annotated photographs organized into over 21,000 categories according to the WordNet noun...

Deep LearningMachine Learning

Inception (deep learning)

Inception is a family of convolutional neural network (CNN) architectures developed by researchers at Google, first introduced in 2014. The original...

Deep LearningNeural Networks

Instance segmentation

Instance segmentation is the computer vision task of detecting every object instance in an image and producing a pixel-precise mask for each one, so that two...

Deep Learning

Intel RealSense D555

The Intel RealSense D555 (also branded simply as RealSense D555 PoE) is a stereoscopic depth camera announced in mid-2025 that is the first product in the...

AI HardwareRobotics

InternVideo

InternVideo is a family of general-purpose video foundation models developed by OpenGVLab at the Shanghai Artificial Intelligence Laboratory in collaboration...

AI ModelsChinese AI

International Conference on Computer Vision

The International Conference on Computer Vision (ICCV) is one of the three top-tier academic conferences in computer vision, held every two years in...

AI Events

Intersection over union (IoU)

Intersection over Union (IoU) is the standard computer vision evaluation metric that measures how well a predicted region overlaps a ground-truth region: it is...

IoU

See also: Machine learning terms Intersection over Union (IoU), also known as the Jaccard index or Jaccard similarity coefficient, is the standard overlap...

Model Evaluation

Jian Sun

Jian Sun (1976 to 2022) was a Chinese computer scientist and one of the most influential researchers in modern computer vision. He is best known as a...

Chinese AIPeople

Joy Buolamwini

Joy Buolamwini is a Canadian-American computer scientist and digital activist known for research exposing racial and gender bias in commercial facial...

AI EthicsPeople

Justin Johnson

Justin Johnson is an American computer scientist known for his work in computer vision and machine learning, particularly on perceptual losses for real-time...

People

Kaiming He

Kaiming He is a Chinese computer scientist known for foundational work in computer vision and deep learning, and is most closely associated with deep residual...

Deep LearningPeople

Keypoints

In computer vision, keypoints (also called interest points, feature points, or salient points) are distinctive locations in an image that can be reliably...

LAION

LAION (Large-scale Artificial Intelligence Open Network) is a German non-profit organization, registered as LAION e.V. in Hamburg, that builds and releases...

Data & DatasetsMachine Learning

LVIS (Large Vocabulary Instance Segmentation)

LVIS (Large Vocabulary Instance Segmentation, pronounced "el-vis") is a large-scale instance segmentation benchmark for computer vision that targets the...

Data & Datasets

Landmarks

Landmarks are reference points used as anchors in two largely separate areas of machine learning. In manifold learning and dimension reduction, landmarks are a...

Machine Learning

Latent diffusion model

A latent diffusion model (LDM) is a type of diffusion model that runs the denoising diffusion process in a compressed latent space learned by a pretrained...

Deep LearningGenerative AI

LeNet

LeNet is the pioneering family of convolutional neural networks developed by Yann LeCun and collaborators at AT&T Bell Labs between roughly 1988 and 1998 to...

Artificial IntelligenceDeep Learning

Luma Dream Machine

Luma Dream Machine is a generative AI video and image platform from Luma AI (Luma Labs, Inc.), a San Francisco company, that turns text prompts and still...

AI ModelsGenerative AI

Lyte

Lyte is an American end-to-end integrated perception company for robotics and physical AI, founded in 2021 and headquartered in Mountain View, California. The...

CompaniesPhysical AI

MM-Vet

MM-Vet is an AI benchmark for evaluating large multimodal models (LMMs, also called multimodal large language models or MLLMs) on tasks that require combining...

AI Benchmarks

MMMU-Pro

MMMU-Pro is a rigorous benchmark for evaluating multimodal AI systems on college-level, expert questions that genuinely require seeing an image, built as a...

AI BenchmarksLarge Language Models

MNIST

The Modified National Institute of Standards and Technology (MNIST) database is a collection of 70,000 grayscale images of handwritten digits (0 through 9)...

Data & DatasetsMachine Learning

Machine learning terms/Computer Vision

The key machine learning terms for computer vision describe how neural networks turn pixels into predictions: a convolution slides a small learned filter...

Machine Learning

Marble (World Labs)

Marble is a multimodal generative world model developed by World Labs, the spatial intelligence startup co-founded by Stanford computer scientist Fei-Fei Li....

AI Tools & ProductsGenerative AI

Mask R-CNN

Mask R-CNN is a deep convolutional neural network for instance segmentation, introduced in 2017 by Kaiming He, Georgia Gkioxari, Piotr Dollar, and Ross...

Deep Learning

Masked autoencoder (MAE)

Masked autoencoder (MAE) is a self-supervised learning method for vision transformers that masks roughly 75% of an input image's patches and trains a network...

Machine LearningTraining & Optimization

MediaPipe

MediaPipe is an open-source, cross-platform framework from Google for building on-device machine learning pipelines that process video, audio, and other...

Developer ToolsGoogle

Megvii

Megvii Technology Limited (Chinese: 旷视科技), also known by the name of its flagship product Face++, is a Beijing-based artificial intelligence company...

AI CompaniesChinese AI

Mistral OCR 3

Mistral OCR 3 is a document-understanding and optical character recognition model from Mistral AI, released in mid-December 2025 as the third generation of the...

AI CompaniesAI Models

MobileNet

MobileNet is a family of efficient convolutional neural network (CNN) architectures developed by Google for mobile and edge AI applications. First introduced...

AI HardwareDeep Learning

Mobileye

Mobileye Global Inc. (Nasdaq: MBLY) is an Israeli technology company headquartered in Jerusalem that develops vision-based advanced driver-assistance systems...

AI CompaniesAI Hardware

Multimodal Model

A multimodal model is an artificial intelligence system that processes, relates, and generates information across two or more types of data, or modalities,...

Deep LearningMachine Learning

Nano Banana

Nano Banana is the codename, later turned official brand, for Google's native image generation and editing models built into the Gemini ecosystem and developed...

AI ModelsGenerative AI

NeRF

Neural Radiance Fields (NeRF) is a method for synthesizing photorealistic novel views of a 3D scene by encoding the scene as a continuous 5D function (3D...

Deep LearningNeural Networks

Nougat (model)

Nougat (Neural Optical Understanding for Academic Documents) is a document-understanding model from Meta AI that converts the rendered image of a document page...

AI ModelsMeta AI

OCR Models

OCR Models are artificial intelligence (AI) systems that convert images of typed, handwritten, or printed text into machine-readable digital text through...

Artificial IntelligenceDeep Learning

Object detection

Object detection is a computer vision task that locates and classifies every object instance in an image or video frame, returning for each one a bounding box,...

Artificial IntelligenceDeep Learning

OpenGVLab

OpenGVLab is the open-source organization and project hub for general-vision and multimodal foundation models run by the General Vision group at Shanghai AI...

Chinese AIOpen Source AI

OpenPose

OpenPose is an open-source library for real-time multi-person 2D pose estimation that detects body, foot, hand, and facial keypoints in images and video....

Open Source AI

PASCAL VOC

PASCAL VOC (Pattern Analysis, Statistical Modelling and Computational Learning Visual Object Classes) is a long-running benchmark dataset and annual challenge...

AI BenchmarksData & Datasets