Computer Vision

Perception Encoder

Perception Encoder (PE) is a family of vision and vision-language encoders from Meta AI's Fundamental AI Research (FAIR) group, released in April 2025, whose...

Meta AIMultimodal AI

Photography

See also: Photography ChatGPT Plugins Artificial intelligence in photography covers a wide span of techniques, from the computational pipelines baked into...

AI Tools & ProductsGenerative AI

Photoroom

Photoroom is an AI-powered photo editing platform headquartered in Paris, France, specializing in background removal, product photography, and generative image...

AI Tools & ProductsImage Generation

Pika 2.5

Pika 2.5 is a generative video model developed by Pika Labs, the San Francisco based AI video startup co-founded in April 2023 by Stanford AI Lab dropouts Demi...

AI ModelsGenerative AI

Pooling

See also: convolutional neural network, convolutional layer, feature map, downsampling Pooling is a downsampling operation in neural networks that aggregates...

Neural Networks

Pose estimation

Pose estimation is the computer vision task of detecting and localizing the keypoints (also called landmarks or joints) of a human body, hand, face, animal, or...

Deep LearningMachine Learning

Pre-training

Pre-training is the first and most compute-intensive stage of building a modern AI model: a neural network is trained on a massive, mostly unlabeled dataset...

Artificial IntelligenceDeep Learning

Project Aria

Project Aria is an egocentric data-collection research program run by Meta's Reality Labs Research. It was announced on September 16, 2020 [1][2]. The program...

Data & DatasetsMeta AI

R-CNN (Regions with CNN features)

R-CNN (short for Regions with CNN features) is a two-stage object detection method that generates about 2,000 candidate region proposals per image with...

Deep Learning

Rerun (rerun.io)

Rerun is an open-source multimodal data stack and visualization system built for robotics, computer vision, and other forms of physical AI. The project is...

Developer ToolsOpen Source AI

ResNet

ResNet (Residual Network) is a deep convolutional neural network architecture introduced by Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun, then at...

Deep LearningNeural Networks

Robot manipulation

Robot manipulation is the ability of a robotic system to physically interact with objects in its environment through grasping, pushing, pulling, inserting,...

Robotics

Robot navigation

Robot navigation is the ability of a mobile robot to determine its own position in its environment, plan a path toward a goal, and execute that path while...

Robotics

Runway Act-Two

Runway Act-Two is a generative motion capture and character animation model developed by Runway, publicly introduced on July 15, 2025. The model accepts a...

AI ModelsGenerative AI

Runway Aleph

Runway Aleph is an in-context AI video editing model from Runway that transforms and edits an existing video clip from a plain-text instruction, performing a...

AI ModelsGenerative AI

SAM 2

SAM 2 (Segment Anything Model 2) is a promptable visual segmentation model for both images and video developed by Meta AI and released on 29 July 2024.[^1] It...

AI ModelsMeta AI

SSD (Single Shot MultiBox Detector)

SSD (Single Shot MultiBox Detector) is a single stage object detection model that predicts bounding boxes and per class confidence scores in one forward pass...

Deep Learning

Saliency map

A saliency map is an explainable AI visualization that highlights which parts of an input, most often the individual pixels of an image, most influenced a deep...

Deep LearningInterpretability

Sapiens (computer vision)

Sapiens is a family of human-centric computer vision foundation models developed by Meta (Reality Labs), introduced in 2024 and presented as an oral paper at...

AI ModelsMeta AI

Seedance

Seedance is the family of foundation video generation models built by the Seed team at ByteDance, the Chinese internet company that owns TikTok and Douyin. The...

AI ModelsChinese AI

Seedream

Seedream is a series of text-to-image and image-editing foundation models built by the Seed research team at ByteDance, the company behind TikTok and Douyin....

AI ModelsChinese AI

Segment Anything Model and Dataset (SAM and SA-1B)

Segment Anything Model (SAM) is a promptable image segmentation foundation model released by Meta AI on April 5, 2023 that lets users "cut out" any object in...

AI ModelsAI Research

Semantic Segmentation

Semantic segmentation is a computer vision task that assigns a category label to every single pixel in an image, producing a dense map in which each pixel...

Deep Learning

SenseTime

SenseTime (Chinese: 商汤科技; pinyin: Shāngtāng Kējì) is a partly state-owned, publicly traded artificial intelligence company headquartered in Hong Kong that grew...

AI CompaniesChinese AI

SigLIP

SigLIP (Sigmoid Loss for Language-Image Pre-training) is a family of vision-language encoders developed by researchers at Google DeepMind that pre-trains image...

Google DeepMindMultimodal AI

SimCLR

SimCLR (Simple Framework for Contrastive Learning of Visual Representations) is a self-supervised learning method for computer vision in which a network is...

Deep LearningMachine Learning

Simultaneous Localization and Mapping (SLAM)

Simultaneous Localization and Mapping (SLAM) is the computational problem of building a map of an unknown environment while at the same time estimating the...

AlgorithmsRobotics

Size invariance

See also: Machine learning terms Size invariance, also called scale invariance, is the property of a model, feature, or algorithm that produces the same output...

Spatial Pooling

Spatial pooling is a downsampling operation in convolutional neural networks (CNNs) that replaces a local region of a feature map with a single summary...

Machine LearningNeural Networks

Spatial intelligence

Spatial intelligence is the ability of an AI system to perceive, understand, reason about, generate, and interact with three-dimensional space rather than just...

Embodied AIGenerative AI

Stride

Stride is the step size by which a filter (or pooling window) moves across the input in a convolutional neural network (CNN): a stride of 1 shifts the filter...

Deep LearningMachine Learning

StyleGAN

StyleGAN is a family of style-based generative adversarial network (GAN) architectures developed by NVIDIA Research for high-quality unconditional image...

Generative AIImage Generation

Swin Transformer

The Swin Transformer (Shifted Window Transformer) is a hierarchical vision transformer architecture that computes self-attention within local, non-overlapping...

Deep LearningNeural Networks

Synthesia 3.0

Synthesia 3.0 is a major release of the AI video generation platform from Synthesia, the London-based company co-founded in 2017 by Victor Riparbelli, Steffen...

AI ModelsGenerative AI

T2I-CompBench

T2I-CompBench is an AI benchmark for evaluating compositional text-to-image generation, introduced in the paper "T2I-CompBench: A Comprehensive Benchmark for...

AI Benchmarks

Topaz Labs

Topaz Labs is a software company headquartered in Dallas, Texas, that develops AI-powered tools for photo and video enhancement, best known for Gigapixel,...

AI Tools & ProductsImage Generation

Translational invariance

Translational invariance (also called translation invariance or shift invariance) is the property of a function, system, or machine learning model whose output...

Deep LearningNeural Networks

U-Net

U-Net is a convolutional neural network architecture designed for biomedical image segmentation. It was introduced by Olaf Ronneberger, Philipp Fischer, and...

Deep LearningMachine Learning

Unconditional Image Generation Models

Unconditional image generation models are generative neural networks that learn the marginal distribution p(x) of a set of training images and produce new...

AI Models

V-JEPA

V-JEPA (Video Joint Embedding Predictive Architecture) is a self-supervised video model from Meta AI that learns by predicting masked regions of a video in an...

AI ModelsMachine Learning

V-JEPA 2

V-JEPA 2 (Video Joint Embedding Predictive Architecture 2) is an open-source video world model released by Meta AI on June 11, 2025 that learns to understand,...

AI ModelsOpen Source AI

VGG

VGG (also called VGGNet) is a deep convolutional neural network architecture, introduced in 2014 by Karen Simonyan and Andrew Zisserman of the Visual Geometry...

Deep LearningNeural Networks

VGGNet

VGGNet is a deep convolutional neural network architecture, introduced in 2014 by Karen Simonyan and Andrew Zisserman of the Visual Geometry Group at the...

AI HistoryAI Models

Video Classification Models

Video classification models are machine learning systems that assign one or more category labels to a video clip, typically describing the human action...

AI Models

Video-MME

Video-MME (Video Multi-Modal Evaluation) is a benchmark for testing how well multimodal large language models (MLLMs) understand video, built from 900 manually...

AI BenchmarksMultimodal AI

Virtual Reality

Virtual reality (VR) is a computer-generated three-dimensional environment that a user can perceive, navigate and interact with in a way that simulates...

AI HardwareAI Tools & Products

Vision Transformer

The Vision Transformer (ViT) is a deep learning architecture that applies the transformer model, originally designed for natural language processing, to image...

Model Architecture

Vision language model

A vision-language model (VLM) is a class of multimodal artificial intelligence model that jointly processes visual inputs (typically still images, sometimes...

Large Language ModelsMultimodal AI

Vision-based tactile sensor

A vision-based tactile sensor, also called an optical or camera-based tactile sensor, is a category of tactile sensing that measures touch by watching it...

Robotics

Visual Question Answering Models

Visual question answering models are AI systems that take an image and a natural language question about that image and return a natural language answer. They...

AI BenchmarksAI Models

WISE

WISE (World Knowledge-Informed Semantic Evaluation) is an AI benchmark that tests whether a text-to-image model actually possesses and correctly applies...

AI Benchmarks

Wan 2.1-VACE

Wan 2.1-VACE (also written Wan2.1-VACE) is an open-weights video creation and editing model released by Alibaba's Tongyi Lab on May 14, 2025 [1][4]. The name...

AI ModelsChinese AI

Wan 2.5

Wan 2.5 is a natively multimodal AI video generation model developed by Alibaba Cloud's Tongyi Lab and previewed at the company's Apsara 2025 conference in...

AI ModelsChinese AI

Wayve

Wayve is a British artificial intelligence company, founded in Cambridge in 2017 by Alex Kendall and Amar Shah, that develops end to end "embodied AI" software...

AI CompaniesAutonomous Vehicles

World Labs

World Labs is an American spatial-intelligence company, headquartered in San Francisco, that builds "Large World Models" (LWMs), generative AI systems that...

AI CompaniesGenerative AI

YOLO (object detection)

YOLO (You Only Look Once) is a family of object detection models that treat detection as a single regression problem, predicting bounding boxes and class...

Deep LearningNeural Networks

Yitu Technology

Yitu Technology (Chinese: 依图科技; pinyin: Yītú Kējì) is a Chinese artificial intelligence company headquartered in Shanghai that was founded in 2012 by Zhu Long...

AI CompaniesChinese AI

Zero-Shot Image Classification Models

Zero-shot image classification models are vision systems that assign images to categories the model has never encountered as labeled training examples. Instead...

AI Models

ZeroBench

ZeroBench is a visual reasoning benchmark built to be effectively impossible for current frontier large multimodal models, which score 0.0% on its main...

AI BenchmarksMultimodal AI

olmOCR

olmOCR is an open toolkit and vision-language model from the Allen Institute for AI (Ai2) that turns PDFs and document images into clean, structured plain text...

Natural Language ProcessingOpen Source AI