Showing 132 open source projects for "camera"

View related business solutions
  • $300 Free Credits to Build on Google Cloud Icon
    $300 Free Credits to Build on Google Cloud

    New customers can spin up VMs, build with AI, and query data at no cost.

    Put 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.
    Start Free
  • Our Free Plans just got better! | Auth0 Icon
    Our Free Plans just got better! | Auth0

    With up to 25k MAUs and unlimited Okta connections, our Free Plan lets you focus on what you do best—building great apps.

    You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
    Try free now
  • 1
    Stable Virtual Camera

    Stable Virtual Camera

    Stable Virtual Camera: Generative View Synthesis with Diffusion Models

    Stable Virtual Camera is a multi-view diffusion model developed by Stability AI that transforms 2D images into immersive 3D videos with realistic depth and perspective. Unlike traditional methods that require complex reconstruction or scene-specific optimization, this model allows users to generate novel views from any number of input images and define custom camera trajectories, enabling dynamic exploration of scenes.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 2
    VGGT-Ω

    VGGT-Ω

    [CVPR 2026 Oral] VGGT Omega

    VGGT-Omega is a Facebook Research computer vision project for feed-forward camera and depth reconstruction. It takes images as input and predicts camera parameters, depth maps, confidence values, and related scene tokens. The project is associated with 3D understanding workflows where models infer scene geometry without a traditional multi-stage reconstruction pipeline. It includes pretrained model variants with different resolutions and text-alignment capabilities, though checkpoint access may require approval. ...
    Downloads: 12 This Week
    Last Update:
    See Project
  • 3
    LLM Vision

    LLM Vision

    Visual intelligence for your home.

    ...It also maintains a timeline of analyzed camera events that can be displayed in dashboards or queried through the assistant interface.
    Downloads: 3 This Week
    Last Update:
    See Project
  • 4
    Slim Camera

    Slim Camera

    Slim Camera - Lightweight RTSP Video Player

    ...Optimized for low resource use, it runs reliably even on older hardware - ideal for background monitoring. Portable, single-file settings and a focus on core functionality make Slim Camera simple, no-fuss video streaming. Support its free, open-source development at https://boosty.to/slim-camera/donate to help keep it ad-free and growing!
    Downloads: 93 This Week
    Last Update:
    See Project
  • Host LLMs in Production With On-Demand GPUs Icon
    Host LLMs in Production With On-Demand GPUs

    NVIDIA L4 GPUs. 5-second cold starts. Scale to zero when idle.

    Deploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
    Start Free
  • 5
    AI Pose Gallery

    AI Pose Gallery

    Chinese version of AI pose reference gallery

    ...The collection organizes poses into four major groups, 26 categories, and 288 named poses. Users can search by pose name, identifier, or category and filter results by camera angle. Five viewing perspectives include front, angled, side, overhead, and low-angle views. An interactive lightbox supports image navigation and high-resolution PNG downloads. The responsive gallery works on desktop and mobile browsers without external JavaScript dependencies. The repository includes translated metadata, original Japanese records, and deployment scripts.
    Downloads: 55 This Week
    Last Update:
    See Project
  • 6
    HunyuanWorld-Voyager

    HunyuanWorld-Voyager

    RGBD video generation model conditioned on camera input

    ...To support training, the team built a scalable data engine that automatically curates large video datasets with camera pose estimation and metric depth prediction. As a result, Voyager delivers state-of-the-art performance on world exploration benchmarks while maintaining photometric, style, and 3D consistency.
    Downloads: 2 This Week
    Last Update:
    See Project
  • 7
    NeuralScreen

    NeuralScreen

    DLSS 5 NR on your whole Windows desktop, in real time with Boost

    ...It processes games, videos, photographs, and other on-screen content without requiring individual application integration. Users can enhance the entire display or select a particular window for processing. Customizable rendering profiles adjust enhancement strength, color, and camera effects. Boost Mode reduces processing resolution to improve performance while preserving the final display resolution. Supported GPUs can also use DLSS Frame Generation, although compatibility varies by RTX generation. A comparison slider reveals differences between processed and original images. The application includes screenshots, audio recording, OBS integration through Spout2, and customizable keyboard shortcuts.
    Downloads: 45 This Week
    Last Update:
    See Project
  • 8
    geo-sleuth

    geo-sleuth

    An agent skill that finds where a photo was taken

    ...Specialized Python scripts collect, score, and rank geographic candidates before the AI agent evaluates the strongest matches. Results include estimated coordinates, camera direction, confidence levels, and supporting visual evidence. Geo-Sleuth integrates with Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and GitHub Copilot.
    Downloads: 35 This Week
    Last Update:
    See Project
  • 9
    openpilot

    openpilot

    Open source driver assistance system

    ...While engaged, openpilot includes camera-based driver monitoring that works both day and night to alert the driver when their eyes are not on the road ahead.
    Downloads: 18 This Week
    Last Update:
    See Project
  • Cut Data Warehouse Costs by 54% Icon
    Cut Data Warehouse Costs by 54%

    Easily migrate from Snowflake, Redshift, or Databricks with free tools.

    BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
    Start Free
  • 10
    VanishCam

    VanishCam

    Webcam disappearance effects

    ...Additional Naruto and Goku modes recreate stylized disappearance and teleportation effects with animations and sounds. The software processes video locally without uploading or recording footage. It supports a live preview, virtual camera workflows, and integration with OBS Studio. Windows users can run a standalone executable or launch the Python scripts for additional effects.
    Downloads: 2 This Week
    Last Update:
    See Project
  • 11
    Transparent Background

    Transparent Background

    This is a background removing tool powered by InSPyReNet

    ...You can easily remove the background from the image or video or bunch of other stuffs when you can make the background transparent! We basically follow the virtual camera settings from pyvirtualcam. If you do not choose to install virtual camera, it will visualize real-time output with cv2.imshow. Use another checkpoint file. Default is trained with composite dataset and will be automatically downloaded if not available.
    Downloads: 2 This Week
    Last Update:
    See Project
  • 12
    Frigate Home Assistant Integration

    Frigate Home Assistant Integration

    Frigate integration for Home Assistant

    ...The project is especially useful for people building local-first camera monitoring systems with object detection, automations, and smart home alerts.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 13
    Extract TOTP/HOTP secrets

    Extract TOTP/HOTP secrets

    Extract one time password (OTP) secrets from QR codes

    The Python script extract_otp_secrets.py extracts one-time password (OTP) secrets from QR codes exported by two-factor authentication (2FA) apps such as "Google Authenticator".
    5.0 out of 5 stars 1 Review
    Downloads: 2 This Week
    Last Update:
    See Project
  • 14
    VGGSfM

    VGGSfM

    VGGSfM: Visual Geometry Grounded Deep Structure From Motion

    VGGSfM is an advanced structure-from-motion (SfM) framework jointly developed by Meta AI Research (GenAI) and the University of Oxford’s Visual Geometry Group (VGG). It reconstructs 3D geometry, dense depth, and camera poses directly from unordered or sequential images and videos. The system combines learned feature matching and geometric optimization to generate high-quality camera calibrations, sparse/dense point clouds, and depth maps in standard COLMAP format. Version 2.0 adds support for dynamic scene handling, dense point cloud export, video-based reconstruction (1000+ frames), and integration with Gaussian Splatting pipelines. ...
    Downloads: 1 This Week
    Last Update:
    See Project
  • 15
    py-xiaozhi

    py-xiaozhi

    Open-source AI assistant ecosystem with MCP integrations

    py-xiaozhi is a free, open-source, Python-based AI assistant framework designed for voice interaction, multimodal processing, and connected device control. It supports real-time voice conversations through asynchronous audio streaming and Opus encoding. Users can interact with AI models through spoken commands, camera input, and visual recognition. Its Model Context Protocol integration provides tools for music playback, screenshots, application management, and device operations. The framework supports offline wake-word detection using Sherpa-ONNX. It also communicates through WebSocket and MQTT protocols with encrypted connections and automatic reconnection. ...
    Downloads: 5 This Week
    Last Update:
    See Project
  • 16
    HunyuanWorld-Mirror

    HunyuanWorld-Mirror

    Fast and Universal 3D reconstruction model for versatile tasks

    HunyuanWorld-Mirror focuses on fast, universal 3D reconstruction that can ingest varied inputs and produce multiple kinds of 3D outputs. The model accepts combinations of images, camera intrinsics and poses, or even depth cues, then reconstructs consistent 3D geometry suitable for downstream rendering or editing. The pipeline emphasizes both speed and flexibility so creators can go from casual captures to assets without elaborate capture rigs. Outputs can include point clouds, estimated camera parameters, and other 3D representations that plug into typical graphics workflows. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 17
    Fast3R

    Fast3R

    Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

    Fast3R is Meta AI’s official CVPR 2025 release for “Towards 3D Reconstruction of 1000+ Images in One Forward Pass.” It represents a next-generation feedforward 3D reconstruction model capable of producing dense point clouds and camera poses for hundreds to thousands of images or video frames in a single inference pass—eliminating the need for slow, iterative structure-from-motion pipelines. Built on PyTorch Lightning and extending concepts from DUSt3R and Spann3r, Fast3R unifies multi-view geometry, depth estimation, and camera registration within a single transformer-based architecture. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 18
    Map-Anything

    Map-Anything

    MapAnything: Universal Feed-Forward Metric 3D Reconstruction

    Map-Anything is a universal, feed-forward transformer for metric 3D reconstruction that predicts a scene’s geometry and camera parameters directly from visual inputs. Instead of stitching together many task-specific models, it uses a single architecture that supports a wide range of 3D tasks—multi-image structure-from-motion, multi-view stereo, monocular metric depth, registration, depth completion, and more. The model flexibly accepts different input combinations (images, intrinsics, poses, sparse or dense depth) and produces a rich set of outputs including per-pixel 3D points, camera intrinsics, camera poses, ray directions, confidence maps, and validity masks. ...
    Downloads: 0 This Week
    Last Update:
    See Project
  • 19
    ML Sharp

    ML Sharp

    Sharp Monocular View Synthesis in Less Than a Second

    ...The core idea is speed: the 3D representation is produced in under a second on a standard GPU, and then the resulting scene can be rendered in real time to generate new views interactively. The representation is metric, meaning it supports camera movements with an absolute scale rather than only relative depth cues, which is useful for consistent viewpoint changes and downstream spatial tasks. The project is structured for reproducibility, with code and assets aimed at demonstrating view synthesis quality, sharp details, and fine structures when rendering high-resolution images.
    Downloads: 4 This Week
    Last Update:
    See Project
  • 20
    gopro-dashboard-overlay

    gopro-dashboard-overlay

    Programs to process GoPro MP4 & Generic GPX/FIT files

    ...The system supports a wide range of layouts, including maps, gauges, and charts, which can be customized through configuration files. It integrates FFmpeg for rendering and supports multiple resolutions and camera modes such as timelapse and timewarp. The tool can also convert metadata into formats like GPX or CSV for further analysis. It is designed for both post-processing workflows and automated video generation pipelines. Overall, it enhances action footage by adding synchronized visual data overlays.
    Downloads: 2 This Week
    Last Update:
    See Project
  • 21
    F1 Race Replay

    F1 Race Replay

    An interactive Formula 1 race visualisation and data analysis tool

    F1 Race Replay is an interactive replay viewer that lets users watch and analyze recorded Formula 1 race sessions with precise control over camera angles, timing, and telemetry overlay, offering a rich experience beyond standard broadcast replays. It ingests official timing and positional data, then renders vehicle movements through track maps and 3D visualizations so fans, analysts, and engineers can review strategy, overtakes, tire degradation effects, and pit stop impacts in detail. ...
    Downloads: 1 This Week
    Last Update:
    See Project
  • 22
    Blender GIS

    Blender GIS

    Blender addons to make the bridge between Blender and geographic data

    ...Manage georeferencing information of a scene, compute a terrain mesh by Delaunay triangulation, drop objects on a terrain mesh, make terrain analysis using shader nodes, set up new cameras from geotagged photos, set up a camera to render with Blender a new georeferenced raster.
    Downloads: 59 This Week
    Last Update:
    See Project
  • 23
    Depth Pro

    Depth Pro

    Sharp Monocular Metric Depth in Less Than a Second

    Depth Pro is a foundation model for zero-shot metric monocular depth estimation, producing sharp, high-frequency depth maps with absolute scale from a single image. Unlike many prior approaches, it does not require camera intrinsics or extra metadata, yet still outputs metric depth suitable for downstream 3D tasks. Apple highlights both accuracy and speed: the model can synthesize a ~2.25-megapixel depth map in around 0.3 seconds on a standard GPU, enabling near real-time applications. The repo and research page emphasize boundary fidelity and crisp geometry, addressing a common weakness in monocular depth where edges can blur. ...
    Downloads: 3 This Week
    Last Update:
    See Project
  • 24
    Frigate

    Frigate

    NVR with realtime local object detection for IP cameras

    Frigate - NVR With Realtime Object Detection for IP Cameras A complete and local NVR designed for Home Assistant with AI object detection. Uses OpenCV and Tensorflow to perform realtime object detection locally for IP cameras. Use of a Google Coral Accelerator is optional, but highly recommended. The Coral will outperform even the best CPUs and can process 100+ FPS with very little overhead.
    Downloads: 54 This Week
    Last Update:
    See Project
  • 25
    The Hypersim Dataset

    The Hypersim Dataset

    Photorealistic Synthetic Dataset for Holistic Indoor Scene

    ...It provides richly annotated renderings—RGB, depth, surface normals, instance and semantic segmentations, and material/lighting metadata—produced from high-fidelity virtual environments. The dataset spans diverse furniture layouts, room types, and camera trajectories, enabling robust training for geometry, segmentation, and SLAM-adjacent tasks. Rendering pipelines and utilities allow researchers to reproduce sequences, generate novel views, or extract task-specific supervision. Because the data are perfectly labeled and controllable, Hypersim is well suited for pretraining and for studying domain transfer to real imagery. ...
    Downloads: 0 This Week
    Last Update:
    See Project