Skip to main content

Computer Vision

Image recognition, generation, video analysis

30 entities indexed

PaperComputer Vision

Learning Transferable Visual Models From Natural Language Supervision (CLIP)

by OpenAI

Introduced CLIP (Contrastive Language-Image Pre-training), a model trained on 400 million image-text pairs using contrastive learning that achieves remarkable zero-shot transfer to diverse vision tasks. CLIP became foundational for vision-language alignment and generative AI pipelines.

clipcontrastive-learningzero-shot
58C+
PaperComputer Vision

High-Resolution Image Synthesis with Latent Diffusion Models (Stable Diffusion)

by CompVis / Stability AI

Introduced Latent Diffusion Models (LDMs), which perform the diffusion process in a compressed latent space rather than pixel space, dramatically reducing computational cost while maintaining image quality. This work underpins Stable Diffusion, the most widely used open-source image generation model.

stable-diffusionlatent-diffusiontext-to-image
58C+
PaperComputer Vision

Segment Anything

by Meta AI

Introduced the Segment Anything Model (SAM) and the SA-1B dataset of 1 billion masks on 11 million images. SAM is a promptable segmentation foundation model that generalizes to new image distributions and tasks without additional training, enabling a new paradigm of interactive segmentation.

segmentationfoundation-modelpromptable
56C+
BenchmarkComputer Vision

ImageNet

by Deng et al. / Stanford / Princeton

ImageNet (ILSVRC) is the foundational large-scale visual recognition benchmark with 1.2 million training images across 1,000 object categories. Top-1 and Top-5 accuracy on the validation set have been the standard measure of progress in image classification for over a decade.

image-classificationvisiontop-1-accuracy
56C+
PaperComputer Vision

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

by Stability AI

Presented SDXL, a significantly improved latent diffusion model architecture featuring a 3.5B parameter UNet backbone with a secondary refiner model, conditioning on image size and crop parameters, and a curated high-aesthetic dataset. SDXL substantially improves visual quality and prompt adherence over prior Stable Diffusion versions.

sdxlstable-diffusiontext-to-image
55C+
DatasetComputer Vision

SA-1B (Segment Anything)

by Meta AI

SA-1B is Meta AI's massive segmentation dataset released alongside the Segment Anything Model (SAM), containing over 1 billion high-quality segmentation masks across 11 million diverse, high-resolution images. It is the largest segmentation dataset ever created and enables training of generalist vision models with strong zero-shot transfer capabilities.

segmentationSAMfoundation-model
54C+
DatasetComputer Vision

Open Images V7

by Google

Google's Open Images V7 is one of the largest existing datasets with object-level annotations, containing approximately 9 million images annotated with image-level labels, object bounding boxes, object segmentation masks, visual relationships, and localized narratives across 600+ object classes.

object-detectionsegmentationvisual-relationships
54C+
ModelComputer Vision

Stable Diffusion XL

by Stability AI

Stability AI's high-resolution image generation model producing photorealistic and artistic images at 1024x1024 resolution. Features a two-stage architecture with a base model and refiner for enhanced detail and compositional quality.

image-generationdiffusionopen-source
53C+
PaperComputer Vision

Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (Imagen)

by Google Brain

Introduced Imagen, a text-to-image diffusion model that leverages large pretrained language models (T5-XXL) for text understanding combined with cascaded diffusion models for image synthesis. Imagen demonstrated that scaling text encoders is more impactful than scaling diffusion models, establishing DrawBench as a new evaluation benchmark.

imagentext-to-imagediffusion
50C+
ScriptComputer Vision

Object Detection Setup

by Ultralytics

Bootstraps a production-ready object detection workflow using YOLOv8 or RT-DETR, including webcam/video stream ingestion, NMS post-processing, and annotation overlay rendering. Outputs annotated frames and a structured JSON detections log suitable for downstream analytics.

object-detectionyolobounding-boxes
50C+
SkillComputer Vision

Object Detection

by AaaS

A core computer vision skill that enables agents to identify and locate objects within an image or video stream. By predicting bounding boxes and class labels for each object, this skill forms the foundation for environmental understanding. It is crucial for applications requiring spatial awareness, from autonomous navigation to automated inspection.

computer-visionobject-detectionbounding-box
50C+
DatasetComputer Vision

Places365

by MIT CSAIL

Places365 is a scene-centric database with 1.8 million training images across 365 scene categories, designed to train and evaluate scene recognition models. The dataset enables models to understand the semantic meaning of places and environments, making it ideal for applications in autonomous driving, robotics, and image retrieval.

scene-recognitionscene-classificationtransfer-learning
49C
ModelComputer Vision

Stable Diffusion 3

by Stability AI

Stable Diffusion 3 is a powerful text-to-image model using a Multimodal Diffusion Transformer (MMDiT) architecture. It excels at generating images with unprecedented text quality, adhering closely to complex prompts, and achieving high photorealism and compositional accuracy compared to its predecessors.

image-generationdiffusiontext-to-image
49C
BenchmarkComputer Vision

VQA v2

by Georgia Tech / VT

Visual Question Answering benchmark requiring models to answer open-ended questions about images. Version 2 balances the dataset to reduce language biases, ensuring models must genuinely understand image content rather than relying on question-type priors.

benchmarkevaluationmultimodal
49C
SkillComputer Vision

Visual Question Answering

by AaaS

Enables agents to answer free-form natural language questions about images by grounding language in visual features. Covers prompt construction for vision-language models, chain-of-thought visual reasoning, and failure modes such as hallucination and spatial confusion.

vqavision-languagemultimodal
49C
BenchmarkComputer Vision

MMMU

by CUHK / Waterloo

MMMU is a challenging multimodal benchmark designed to evaluate large models on expert-level tasks. It contains over 11,500 college-level problems spanning six core disciplines, requiring models to integrate deep subject knowledge with visual perception to answer multiple-choice questions with detailed reasoning.

benchmarkevaluationmultimodal
48C
ScriptComputer Vision

OCR Pipeline Script

by Community

This script provides a sophisticated OCR pipeline that intelligently routes documents to the most suitable engine—Tesseract, PaddleOCR, or a cloud API—based on image quality analysis. It processes various document types and outputs structured JSON containing text sorted by reading order, complete with bounding box coordinates and confidence scores for each word or line.

ocrtext-extractiondocument-ai
48C
SkillComputer Vision

OCR Pipeline

by AaaS

Builds end-to-end pipelines for extracting structured text from images, scanned documents, and PDFs using OCR engines combined with layout analysis. Teaches preprocessing, engine selection (Tesseract, PaddleOCR, Google Document AI), post-correction, and handoff to language models for structured extraction.

ocrdocument-parsingtext-extraction
48C
DatasetComputer Vision

ShareGPT4V

by Shanghai AI Lab

ShareGPT4V is a large-scale, high-quality dataset containing 100,000 image-text pairs generated by GPT-4V. It is specifically designed for the instruction-tuning of open-source large vision-language models (LVLMs). The dataset's detailed captions and conversational QA pairs significantly enhance a model's ability to perform complex scene understanding, OCR, and visual reasoning.

datasetmultimodalinstruction-tuning
47C
ScriptComputer Vision

Image Classification Pipeline

by Community

End-to-end image classification pipeline that handles dataset loading, preprocessing, model inference, and result export using PyTorch and torchvision. Supports batch inference against any Hugging Face ViT or ResNet checkpoint with configurable confidence thresholds.

image-classificationvisionpytorch
47C
ScriptComputer Vision

Image Segmentation Script

by Meta AI

Runs Segment Anything Model (SAM 2) or Mask2Former on image batches, producing per-pixel segmentation masks with class labels and confidence scores. Includes utilities for mask overlay visualization and RLE-encoded mask export compatible with COCO annotation format.

segmentationsammask
46C
ModelComputer Vision

Sora

by OpenAI

Sora is a text-to-video diffusion transformer model by OpenAI that generates high-fidelity, minute-long videos from textual prompts. It demonstrates an advanced understanding of language and the physical world, enabling complex scenes with multiple characters, specific motions, and coherent narratives.

video-generationtext-to-videoopenai
45C
ScriptComputer Vision

Visual Search Engine

by Community

This script provides a complete framework for building a multimodal visual search engine. It uses CLIP to generate image and text embeddings, which are indexed in a vector database like Qdrant or Weaviate for efficient similarity search. The system supports both text-to-image and image-to-image queries and includes a FastAPI server for API access.

visual-searchimage-embeddingssimilarity-search
44C
DatasetComputer Vision

WebVid-10M

by University of Oxford

WebVid-10M is a massive dataset containing over 10 million video clips paired with descriptive text captions. Scraped from stock video websites, it serves as a foundational pretraining corpus for state-of-the-art video-language models, facilitating research in video understanding, retrieval, and generation.

multimodalvideo-textvideo-captioning
43C
ModelComputer Vision

Veo 2

by Google DeepMind

Google DeepMind's state-of-the-art video generation model capable of producing high-resolution cinematic clips from text prompts. Supports diverse styles, camera controls, and realistic physics simulation.

video-generationtext-to-videodiffusion
43C
BenchmarkComputer Vision

MathVista

by UCLA

Mathematical reasoning benchmark requiring visual understanding of charts, plots, geometry diagrams, and infographics. Tests the intersection of visual perception and mathematical reasoning with 6,141 problems from 28 existing datasets and 3 newly collected ones.

benchmarkevaluationmultimodal
43C
SkillComputer Vision

Video Understanding

by AaaS

Covers temporal reasoning over video streams, including frame sampling strategies, action recognition, scene change detection, and dense video captioning. Teaches agents to leverage video-native models (Gemini 1.5 Pro, Video-LLaVA) and build efficient pipelines that avoid processing every frame.

videotemporalaction-recognition
43C
ModelComputer Vision

TripoSR

by Stability AI / Tripo AI

TripoSR is a fast, open-source image-to-3D reconstruction model developed by Stability AI and Tripo AI that generates high-quality 3D meshes from a single image in under 0.5 seconds on modern hardware. It is based on the Large Reconstruction Model (LRM) architecture and represents a step-change in accessible, real-time single-image 3D reconstruction quality.

3d-generationimage-to-3dsingle-image
40C
BenchmarkComputer Vision

RealWorldQA

by xAI

Benchmark testing multimodal models on practical real-world visual understanding tasks. Features questions about real photographs requiring spatial reasoning, object recognition, scene understanding, and practical knowledge that goes beyond simple object detection.

benchmarkevaluationmultimodal
40C
SkillComputer Vision

Visual Grounding

by AaaS

Trains agents to localize specific image regions described by natural language referring expressions, bridging the gap between language and spatial visual understanding. Covers grounding models (Grounding DINO, Grounded SAM), evaluation metrics (R@k, mAP), and integration into tool-use agents for UI automation and document analysis.

groundingreferring-expressionregion
37D