Search Results for "vision" - Page 3
Sort By:
Showing 271 open source projects for "vision"
View related business solutions-
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
DINOv2
PyTorch code and models for the DINOv2 self-supervised learning
DINOv2 is a self-supervised vision learning framework that produces strong, general-purpose image representations without using human labels. It builds on the DINO idea of student–teacher distillation and adapts it to modern Vision Transformer backbones with a carefully tuned recipe for data augmentation, optimization, and multi-crop training. The core promise is that a single pretrained backbone can transfer well to many downstream tasks—from linear probing on classification to retrieval, detection, and segmentation—often requiring little or no fine-tuning. ... -
2
Generative AI
Sample code and notebooks for Generative AI on Google Cloud
...The README emphasises getting started with prompts, datasets, environments and sample apps, making it ideal for both experimentation and production-ready usage. The repository architecture is organised into folders like gemini/, search/, vision/, audio/, and rag-grounding/, which helps developers locate use cases by modality. It is licensed under Apache-2.0, opensourced and maintained by Google, meaning it's designed with enterprise-grade practices in mind. Overall, it serves as a practical entry point and reference library for building real-world generative AI systems on Google Cloud. -
3
AI-Tutorials/Implementations Notebooks
Codes/Notebooks for AI Projects
...The repository contains numerous Jupyter notebooks and code samples that demonstrate modern techniques in machine learning, deep learning, data science, and large language model workflows. It includes implementations for a wide range of AI topics such as computer vision, agent systems, federated learning, distributed systems, adversarial attacks, and generative AI. Many of the tutorials focus on building AI agents, multi-agent systems, and workflows that integrate language models with external tools or APIs. The codebase acts as a hands-on learning resource, allowing users to experiment with new frameworks, architectures, and machine learning workflows through guided examples. -
4
qxresearch-event-1
Python hands on tutorial with 50+ Python Application
...The repository contains dozens of small programs, many implemented with minimal lines of code, covering topics such as machine learning, graphical user interfaces, computer vision, and API integration. Each example is designed to illustrate a single concept or application in a clear and concise manner so that learners can quickly understand the underlying logic. The project emphasizes practical experimentation, allowing beginners to modify and extend the example programs to explore new ideas. Many of the examples are accompanied by video explanations that guide learners through the code and demonstrate how the programs work in practice. -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
5
BoxMOT
Pluggable SOTA multi-object tracking modules for segmentation
BoxMOT is an open-source framework designed to provide modular implementations of state-of-the-art multi-object tracking algorithms for computer vision applications. The project focuses on the tracking-by-detection paradigm, where objects detected by vision models are continuously tracked across frames in a video sequence. It provides a pluggable architecture that allows developers to combine different object detectors with multiple tracking algorithms without modifying the core codebase. ... -
6
Skyvern
Automate browser-based workflows with LLMs and Computer Vision
Skyvern uses a combination of computer vision and AI to understand content on a webpage, making it adaptable to any website. Skyvern takes instructions in natural language, allowing it to execute complex objectives with simple commands. Skyvern is an API-first product. Workflows execute in the cloud, allowing it to run hundreds of workflows at the same time. Skyvern's AI decisions come with built-in explanations, providing clear summaries and justifications for every action. -
7
fastai
Deep learning library
fastai is a deep learning library which provides practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains, and provides researchers with low-level components that can be mixed and matched to build new approaches. It aims to do both things without substantial compromises in ease of use, flexibility, or performance. This is possible thanks to a carefully layered architecture, which expresses common underlying... -
8
Windows-MCP
MCP server enabling AI agents to control and automate Windows OS
...Windows-MCP provides capabilities such as file navigation, application management, UI interaction, and QA testing workflows, making it suitable for building autonomous desktop agents. It focuses on native interaction with Windows UI elements rather than relying on traditional computer vision techniques, which simplifies integration and improves efficiency. It includes a set of tools that simulate user inputs like keyboard and mouse actions while also capturing the current state of windows and interfaces. It is designed to be extensible and adaptable, allowing developers to customize or expand its functionality for different automation or AI use cases. -
9
StarVector
StarVector is a foundation model for SVG generation
...The system treats vector graphics creation as a code generation problem, producing SVG code that can render detailed vector images. Its architecture combines computer vision techniques with language modeling capabilities so it can understand visual inputs and textual prompts simultaneously. The model converts raster images or text instructions into structured vector representations, enabling high-quality vectorization and design generation. This approach allows StarVector to create scalable graphics that maintain visual quality regardless of resolution, which is especially useful for design tools and illustration workflows. ... -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
10
RuView
Turn WiFi signals into real-time human sensing and spatial awareness.
...Built on the concept of WiFi DensePose, it analyzes disturbances in WiFi Channel State Information (CSI) caused by human movement to reconstruct body position, breathing patterns, heart rate, and presence. Unlike traditional vision systems, RuView operates without cameras, wearables, or cloud connectivity, making it a privacy-first sensing solution. The system runs on low-cost hardware such as ESP32 sensor meshes and performs signal processing and machine learning directly at the edge. By learning the RF signature of each environment over time, RuView adapts automatically to different spaces and improves its sensing accuracy. ... -
11
autoMate
AI tool for automating desktop tasks via natural language input
autoMate is an AI-powered local automation tool designed to enable users to control and automate their computers using natural language instructions instead of traditional scripting or rule-based systems. It combines large language models with computer vision techniques to interpret user intent and understand on-screen content, allowing it to interact with graphical interfaces similarly to a human user. autoMate follows an observe-decide-act workflow, where it analyzes the screen, plans actions, and executes them through simulated input such as mouse clicks and keyboard events. Unlike conventional RPA tools that require predefined workflows, autoMate dynamically adapts to tasks by making autonomous decisions based on the current interface state. autoMate emphasizes local execution, meaning all processing happens on the user’s machine to maintain privacy and data security. -
12
vim-ai
AI-powered code assistant for Vim. OpenAI and ChatGPT plugin for Vim
...Its command set covers text completion, editing, chat continuation, image generation, and debugging utilities, making it more versatile than a narrow autocomplete add-on. The repository also highlights support for custom roles, vision features such as image-to-text, and an emerging provider-plugin model for extending compatibility further. A notable design point is that it only sends content the user explicitly selects or includes in prompts, which helps users control what is shared with the external model. -
13
DriveLM
Driving with Graph Visual Question Answering
DriveLM is a research-oriented framework and dataset designed to explore how vision-language models can be integrated into autonomous driving systems. The project introduces a new paradigm called graph visual question answering that structures reasoning about driving scenes through interconnected tasks such as perception, prediction, planning, and motion control. Instead of treating autonomous driving as a purely sensor-driven pipeline, DriveLM frames it as a reasoning problem where models answer structured questions about the environment to guide decision making. ... -
14
GLM-4.1V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
...Though smaller in scale, GLM-4.1V maintains competitive performance, particularly impressive on many benchmarks for models of its size: in fact, on a number of multimodal reasoning and vision-language tasks it outperforms some much larger models from other families. It represents a trade-off: somewhat reduced capacity compared to 4.5V or 4.6V, but with benefits in terms of speed, deployability, and lower hardware requirements — making it especially useful for developers experimenting locally, building lightweight agents, or deploying on limited infrastructure. ... -
15
Alpamayo 1
Bridging Reasoning and Action Prediction
...The model is designed as a foundational component rather than a complete driving stack, allowing developers to build custom autonomous vehicle applications on top of it. It incorporates vision-language-action modeling, enabling it to process sensor data and contextual information simultaneously. Alpamayo supports tasks such as trajectory prediction, auto-labeling, and reasoning-based decision making. The system is optimized for high-performance GPU environments and is intended primarily for experimentation and benchmarking. ... -
16
FastViT
This repository contains the official implementation of research
...Training and inference recipes highlight straightforward integration into common vision tasks such as classification, detection, and segmentation. The codebase provides reference implementations and checkpoints that make it easy to evaluate or fine-tune on downstream datasets. In practice, FastViT offers drop-in backbones that reduce compute and memory pressure without exotic training tricks. -
17
Sparrow
Structured data extraction and instruction calling with ML, LLM
...The system focuses on transforming complex documents such as invoices, receipts, forms, and scanned pages into structured formats like JSON that can be processed by downstream applications. It combines several components, including OCR pipelines, vision-language models, and LLM-based reasoning modules to identify and extract meaningful data fields from heterogeneous document layouts. The architecture is modular, allowing developers to build customizable processing pipelines that integrate with external tools and data extraction frameworks. Sparrow also includes workflow orchestration tools that allow multiple extraction tasks to be combined into automated pipelines for large-scale document processing. -
18
Flax
Flax is a neural network library for JAX
...Flax emphasizes composability: optimizers, training loops, and checkpointing are provided as examples or utilities rather than monolithic frameworks, encouraging research-friendly customization. The library is widely used in vision, language, and reinforcement learning, often serving as a thin layer atop NumPy-like JAX primitives. Tutorials and examples show patterns for multi-host training, mixed precision, and advanced input pipelines that scale from laptops to TPUs. -
19
VGGT
[CVPR 2025 Best Paper Award] VGGT
VGGT is a transformer-based framework aimed at unifying classic visual geometry tasks—such as depth estimation, camera pose recovery, point tracking, and correspondence—under a single model. Rather than training separate networks per task, it shares an encoder and leverages geometric heads/decoders to infer structure and motion from images or short clips. The design emphasizes consistent geometric reasoning: outputs from one head (e.g., correspondences or tracks) reinforce others (e.g., pose... -
20
Phone Harness
Let your agent control your phone
...It requires no jailbreak, Xcode project, WebDriverAgent, or custom software installed on the phone. Screenshots of the mirrored window provide visual input, while Apple's Vision framework extracts visible text and tap-ready coordinates. macOS CGEvents supply taps, long presses, drags, scrolling, keyboard input, and iPhone Mirroring shortcuts. After performing an action, the agent captures the screen again to verify the actual resulting state. The harness can be installed as an agent skill for systems such as Claude Code or Codex. ... -
21
docext
An on-premises, OCR-free unstructured data extraction
docext is a document intelligence toolkit that uses vision-language models to extract structured information from documents such as PDFs, forms, and scanned images. The system is designed to operate entirely on-premises, allowing organizations to process sensitive documents without relying on external cloud services. Unlike traditional document processing pipelines that rely heavily on optical character recognition, docext leverages multimodal AI models capable of understanding both visual and textual information directly from document images. ... -
22
CUDA Containers for Edge AI & Robotics
Machine Learning Containers for NVIDIA Jetson and JetPack-L4T
...These containers simplify the deployment of complex machine learning environments by bundling libraries such as CUDA, TensorRT, and deep learning frameworks into reproducible container images. The project is particularly useful for developers building edge AI and robotics systems that rely on GPU-accelerated inference and real-time computer vision. By using containerized environments, developers can ensure that their applications run consistently across different Jetson platforms and JetPack versions. The repository also includes build tools and package management utilities that help automate the process of assembling machine learning environments. -
23
VLMEvalKit
Open-source evaluation toolkit of large multi-modality models (LMMs)
VLMEvalKit is an open-source evaluation toolkit designed for benchmarking large vision-language models that combine visual understanding with natural language reasoning. The toolkit provides a unified framework that allows researchers and developers to evaluate multimodal models across a wide range of datasets and standardized benchmarks with minimal setup. Instead of requiring complex data preparation pipelines or multiple repositories for each benchmark, the system enables evaluation through simple commands that automatically handle dataset loading, model inference, and metric computation. ... -
24
Sapiens
High-resolution models for human tasks
Sapiens is a research framework from Meta AI focused on embodied intelligence and human-like multimodal learning, aiming to train agents that can perceive, reason, and act in complex environments. It integrates sensory inputs such as vision, audio, and proprioception into a unified learning architecture that allows agents to understand and adapt to their surroundings dynamically. The project emphasizes long-horizon reasoning and cross-modal grounding—connecting language, perception, and action into a single agentic model capable of following abstract goals. It includes simulation environments, datasets, and benchmarks for testing grounded understanding, imitation learning, and decision-making. ... -
25
UI-TARS
UI-TARS-desktop version that can operate on your local personal device
UI-TARS is an open-source multimodal “GUI agent” created by ByteDance: a model designed to perceive raw screenshots (or rendered UI frames), reason about what needs to be done, and then perform real interactions with graphical user interfaces (GUIs) — like clicking, typing, navigating menus — across desktop, browser, mobile, or game environments. Rather than relying on rigid, manually scripted UI automation, UI-TARS uses a unified vision-language model (VLM) that integrates perception, reasoning, grounding, and action into one end-to-end framework: it “thinks before acting,” enabling flexible, general-purpose automation. This allows it to perform complex, multi-step tasks such as filling forms, downloading files, navigating applications, and even controlling in-game actions — all by understanding the UI as a human would. ...
