Skip to main content
AdOpenFree logoPromote your productReach more potential users and drive product growth and revenue.Advertise
Favicon of OpenMVS

OpenMVS

Free Listing

OpenMVS is an open-source C++ computer-vision library for Multi-View Stereo reconstruction. It takes camera poses and a sparse point cloud from Structure-from-Motion and produces a dense point cloud, refined mesh, and textured 3D model.

Visit cdcseacave/openMVS

Overview

OpenMVS is a C++ library for computer-vision scientists and the Multi-View Stereo reconstruction community. It fills the last part of the photogrammetry chain after Structure-from-Motion, taking camera poses and a sparse point cloud and producing a textured mesh.

Key Features

  • Dense point-cloud reconstruction for obtaining a complete and accurate as possible point cloud.
  • Mesh reconstruction for estimating a mesh surface that best explains the input point cloud.
  • Mesh refinement for recovering fine details.
  • Mesh texturing for computing a sharp and accurate texture to color the mesh.
  • A scalable pipeline that splits large scenes into sub-scenes when memory is insufficient, reconstructs them sequentially, and merges the results.
  • Continuous integration for Windows, Ubuntu, and macOS x64, with automatic Windows x64 binary builds available for each commit on its Artifacts page.

Use Cases

  • Turning camera-aligned images and sparse Structure-from-Motion geometry into dense point clouds, refined meshes, and textured 3D models.
  • Photogrammetry projects that need to reconstruct large scenes that may not fit available memory.
  • Computer-vision research and practitioner workflows that require a complete dense-to-texture reconstruction chain.
  • Trying OpenMVS on Windows without compiling by using the automatic x64 binary artifacts.

Getting Started

  • Clone the repository from the cdcseacave/openMVS GitHub repository.
  • Follow the building wiki page for platform-specific setup on Windows, Ubuntu, or macOS x64.
  • On Windows, optionally use an automatic x64 binary from the Artifacts page for a commit.
  • Review the usage example on the wiki to understand the input format and module flow.
  • For large scenes, run scripts/python/MvsScalablePipeline.py scene.mvs.

Deployment & Requirements

  • OpenMVS is a C++ library.
  • Building instructions are provided on the project wiki for Windows, Ubuntu, and macOS x64.
  • CI covers Windows, Ubuntu, and macOS x64 builds, and automatic Windows x64 binary builds are posted for each commit.
  • The scalable large-scene pipeline can split a scene into sub-scenes to fit the memory available on the machine.

Before You Adopt

  • License: AGPL-3.0. Review its terms before using, modifying, or distributing the project.
  • OpenMVS expects prior Structure-from-Motion output: camera poses and a sparse point cloud.
  • Large scenes may not fit available memory; the scalable pipeline splits them into sub-scenes, reconstructs them one after the other, and merges the results.
  • The project targets researchers and practitioners rather than casual users.
  • Detailed documentation is kept on the wiki because the README is deliberately lean.

Comments

Sign in to leave a comment.

More like OpenMVS

Favicon of mcp-for-blender-pro

mcp-for-blender-pro

Free ListingStars: 1K

AI assistant and MCP server for Blender

3D Generation & DesignMCP Servers & Tool Connectors

An AI assistant and MCP server for Blender with visual chat, scene inspection and editing tools, multi-agent workflows, and support for OpenAI, Claude, Gemini, Ollama, OpenCode, and custom endpoints.

Favicon of Pascal Editor

Pascal Editor

Free ListingStars: 25K

Open-source local-first 3D building editor

3D Generation & Design

Pascal Editor is an open-source, local-first 3D building editor built with React Three Fiber and WebGPU. It runs in the browser or from a local CLI and lets AI agents connect through MCP.

Favicon of Hunyuan3D

Hunyuan3D

Free ListingStars: 15K

All-in-one AI creation platform for 3D content

3D Generation & Design

Hunyuan3D is an all-in-one AI creation platform for 3D content. It supports text-to-3D, image-to-3D, 3D animation, texture generation, sketch-to-3D, and 3D characters, with low-poly advantages. It targets high-resolution textured 3D assets