Search Results for "vision" - Page 5
Sort By:
Showing 271 open source projects for "vision"
View related business solutions-
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
1
HunyuanOCR
OCR expert VLM powered by Hunyuan's native multimodal architecture
HunyuanOCR is an open-source, end-to-end OCR (optical character recognition) Vision-Language Model (VLM) developed by Tencent‑Hunyuan. It’s designed to unify the entire OCR pipeline, detection, recognition, layout parsing, information extraction, translation, and even subtitle or structured output generation, into a single model inference instead of a cascade of separate tools. Despite being fairly lightweight (about 1 billion parameters), it delivers state-of-the-art performance across a wide variety of OCR tasks, outperforming many traditional OCR systems and even other multimodal models on benchmark suites. ... -
2
FLUX.2
Official inference repo for FLUX.2 models
...It supports high-resolution output (up to ~4 megapixels), which allows for photography-quality images, detailed product shots, infographics or UI mockups rather than just low-resolution drafts. FLUX.2 is built with a modern architecture (a flow-matching transformer + a revamped VAE + a strong vision-language encoder), enabling strong prompt adherence, correct rendering of text/typography in images, reliable lighting, layout, and physical realism, and consistent style/character/product identity across multiple generations or edits. -
3
GLM-4.6V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.6V represents the latest generation of the GLM-V family and marks a major step forward in multimodal AI by combining advanced vision-language understanding with native “tool-call” capabilities, long-context reasoning, and strong generalization across domains. Unlike many vision-language models that treat images and text separately or require intermediate conversions, GLM-4.6V allows inputs such as images, screenshots or document pages directly as part of its reasoning pipeline — and can output or act via tools seamlessly, bridging perception and execution. ... -
4
robosuite
A Modular Simulation Framework and Benchmark for Robot Learning
Robosuite is a modular and extensible simulation framework for robotic manipulation tasks, built on top of MuJoCo. Developed by the ARISE Initiative, Robosuite offers a set of standardized benchmarks and customizable environments designed to advance research in robotic manipulation, control, and imitation learning. It emphasizes realistic simulations and ease of use for both single-task and multi-task learning. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
DeepSparse
Sparsity-aware deep learning inference runtime for CPUs
A sparsity-aware enterprise inferencing system for AI models on CPUs. Maximize your CPU infrastructure with DeepSparse to run performant computer vision (CV), natural language processing (NLP), and large language models (LLMs). -
6
Ultralytics
Ultralytics YOLO
Ultralytics is a comprehensive computer vision framework that provides state-of-the-art implementations of the YOLO (You Only Look Once) family of models, enabling developers to perform tasks such as object detection, segmentation, classification, tracking, and pose estimation within a unified system. It is designed to be fast, accurate, and easy to use, offering both command-line and Python-based interfaces for training, validation, and deployment of machine learning models. -
7
NVIDIA Model Optimizer
A unified library of SOTA model optimization techniques
...The library is designed to reduce model size and computational requirements while maintaining accuracy, making it particularly valuable for deploying large models in production environments. It supports a wide range of model types, including large language models, diffusion models, and vision-language models, and integrates with deployment frameworks such as TensorRT and vLLM. By providing standardized workflows and APIs, it enables developers to experiment with different optimization strategies and select the best approach for their use case. -
8
Android Use
Automate native Android apps with AI using accessibility APIs
...The project works by using Android’s accessibility API to extract structured UI state (as XML) from the device, which is then fed to a large language model (LLM) like OpenAI’s models for decision-making, and actions are executed via the Android Debug Bridge (ADB). This approach bypasses expensive vision-based models and provides faster, cheaper automation with fine-grained interaction capabilities (for example, tapping buttons, typing text, navigating screens). -
9
OpenCV
Open Source Computer Vision Library
The Open Source Computer Vision Library has >2500 algorithms, extensive documentation and sample code for real-time computer vision. It works on Windows, Linux, Mac OS X, Android, iOS in your browser through JavaScript. Languages: C++, Python, Julia, Javascript Homepage: https://opencv.org Q&A forum: https://forum.opencv.org/ Documentation: https://docs.opencv.org Source code: https://github.com/opencv Please pay special attention to our tutorials! -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
10
DeepSeek-OCR
Contexts Optical Compression
DeepSeek-OCR is an open-source optical character recognition solution built as part of the broader DeepSeek AI vision-language ecosystem. It is designed to extract text from images, PDFs, and scanned documents, and integrates with multimodal capabilities that understand layout, context, and visual elements beyond raw character recognition. The system treats OCR not simply as “read the text” but as “understand what the text is doing in the image”—for example distinguishing captions from body text, interpreting tables, or recognizing handwritten versus printed words. ... -
11
The AI Scientist-v2
Workshop-Level Automated Scientific Discovery via Agentic Tree Search
...A key innovation is its progressive agentic tree search, which systematically explores experimental paths and is coordinated by an experiment manager agent that guides decision-making. The system also integrates automated review mechanisms, including vision-language feedback loops, to iteratively refine the quality of generated research outputs. -
12
NitroGen
A Foundation Model for Generalist Gaming Agents
NitroGen is a foundation model for generalist gaming agents developed under the MineDojo initiative, aimed at training a vision-action AI that can play and interact with a wide variety of games by taking pixel inputs and predicting gamepad actions. As an open research model, NitroGen is trained on extensive gameplay data spanning thousands of hours and hundreds of games to instill broad, generalizable gaming competency rather than skill at a single title. This approach enables the model to... -
13
verl-agent
Designed for training LLM/VLM agents via RL
verl-agent is an open-source reinforcement learning framework designed to train large language model agents and vision-language model agents for complex interactive environments. Built as an extension of the veRL reinforcement learning infrastructure, the project focuses on enabling scalable training for agents that perform multi-step reasoning and decision-making tasks. The framework supports multi-turn interactions between agents and their environments, allowing the system to receive feedback after each step and adjust its strategy accordingly. ... -
14
Surya
Implementation of the Surya Foundation Model for Heliophysics
...It is designed to forecast solar phenomena—such as flares, solar wind, irradiance, and active region behavior—by predicting future solar images with a sophisticated long–short vision transformer architecture, thereby enabling improved space weather forecasting. Foresees solar flares, wind, EUV spectra, and active region formation in advance. Achieves approximately 16% improvement in forecasting accuracy over traditional methods. 366-million‑parameter foundation model capturing general-purpose solar representations. -
15
GR00T Whole-Body Control (WBC)
Welcome to GR00T Whole-Body Control (WBC)
...The GEAR-SONIC system learns a broad set of natural motor skills from large-scale human motion data through a unified tracking policy. Released Unitree G1 checkpoints support motion references, whole-body teleoperation, planning, and vision-language-action workflows. A C++ and TensorRT inference stack provides real-hardware deployment, while PyTorch checkpoints support Isaac Lab evaluation and continued training. The repository also includes VR teleoperation, data collection, kinematic planning, and low-latency control configurations. MotionBricks adds real-time latent motion generation for interactive animation and robotics applications. -
16
llm-ollama
LLM plugin providing access to models running on an Ollama server
...The plugin supports both local and remote Ollama servers, allowing flexible deployment scenarios ranging from local machines to cloud-hosted environments. It includes support for multimodal inputs such as image attachments, enabling interaction with vision-capable models. The system also integrates tool usage, allowing models to call predefined utilities such as web search and fetch operations to enhance responses. Additionally, it supports structured outputs through JSON schemas and asynchronous execution for advanced workflows. -
17
scikit-image
Image processing in Python
...We pride ourselves on high-quality, peer-reviewed code, written by an active community of volunteers. scikit-image builds on scipy.ndimage to provide a versatile set of image processing routines in Python. This library is developed by its community, and contributions are most welcome! Read about our mission, vision, and values and how we govern the project. Major proposals to the project are documented in SKIPs. The scikit-image community consists of anyone using or working with the project in any way. A community member can become a contributor by interacting directly with the project in concrete ways. -
18
AutoCrop-Vertical
Smart video converter using YOLOv8 and FFmpeg
AutoCrop-Vertical is a Python-based video processing tool that automatically converts horizontal videos into vertical formats optimized for social media platforms. It uses computer vision techniques and AI models such as YOLOv8 to analyze each frame, detect subjects, and dynamically adjust cropping decisions. Instead of applying a static center crop, the system intelligently tracks people or key objects to preserve visual focus and composition. When cropping would degrade the scene, it can switch to alternative layouts such as letterboxing to maintain context. ... -
19
Moondream
Tiny vision language model
Moondream is a creative code project and visual experimentation repository that explores generative graphics, aesthetic patterns, and interactive art through code. The project typically showcases procedural visualizations, algorithmic designs, and artistic experiments that push the boundaries of what can be expressed with programming languages and rendering frameworks. While the exact nature can vary by commit or branch, Moondream’s work often blends geometry, color theory, and motion to... -
20
GLM-V
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning
GLM-V is an open-source vision-language model (VLM) series from ZhipuAI that extends the GLM foundation models into multimodal reasoning and perception. The repository provides both GLM-4.5V and GLM-4.1V models, designed to advance beyond basic perception toward higher-level reasoning, long-context understanding, and agent-based applications. GLM-4.5V builds on the flagship GLM-4.5-Air foundation (106B parameters, 12B active), achieving state-of-the-art results on 42 benchmarks across image, video, document, GUI, and grounding tasks. ... -
21
Airbyte
Data integration platform for ELT pipelines from APIs, databases
We believe that only an open-source solution to data movement can cover the long tail of data sources while empowering data engineers to customize existing connectors. Our ultimate vision is to help you move data from any source to any destination. Airbyte already provides the largest catalog of 300+ connectors for APIs, databases, data warehouses, and data lakes. Moving critical data with Airbyte is as easy and reliable as flipping on a switch. Our teams process more than 300 billion rows each month for ambitious businesses of all sizes. ... -
22
LISA
LISA: Reasoning Segmentation via Large Language Model
LISA is an open-source multimodal AI system designed to enable language models to perform pixel-level reasoning and segmentation tasks on images. The project introduces a framework where a large language model can interpret natural language instructions and produce segmentation masks that highlight relevant regions in an image. Instead of relying solely on predefined object categories, the model is capable of reasoning about complex textual queries and translating them into visual... -
23
SpikingJelly
SpikingJelly is an open-source deep learning framework
SpikingJelly is an open-source deep learning framework for spiking neural networks that is primarily built on top of PyTorch and aimed at neuromorphic computing research. The project provides the components needed to build, train, and evaluate neural models that communicate through discrete spikes rather than the continuous activations used in conventional artificial neural networks. This makes it especially relevant for researchers interested in biologically inspired computing, event-driven... -
24
SteadyDancer
Harmonized and Coherent Human Image Animation
SteadyDancer is a research-oriented motion stabilization and dancer tracking system designed to analyze and correct motion in videos, making captured performances appear smoother and more stable while preserving expressiveness. It employs computer vision and motion modeling to estimate and reduce unwanted jitters, shakes, or camera wobbles — particularly in dance or movement sequences where traditional smoothing would distort intentional motion. By differentiating between intentional rhythmic motion and unintentional instability, SteadyDancer applies adaptive filtering that enhances video quality without flattening the core movement dynamics. ... -
25
Datumaro
Dataset Management Framework, a Python library and a CLI tool to build
Datumaro is a flexible Python-based dataset management framework and command-line tool for building, analyzing, transforming, and converting computer vision datasets in many popular formats. It supports importing and exporting annotations and images across a wide variety of standards like COCO, PASCAL VOC, YOLO, ImageNet, Cityscapes, and many more, enabling easy integration with different training pipelines and tools. Datumaro makes it easy to merge datasets, split them into training/validation/test subsets, filter or transform annotations, and validate annotation quality — all while preserving metadata and supporting detailed statistics. ...
