COLMAP vs OpenMVG

COLMAP is a free pipeline for reconstructing scenes in 3D from ordered or unordered image collections. Its Structure-from-Motion stage estimates camera poses and sparse 3D structure; its Multi-View Stereo stage uses PatchMatch stereo and stereo fusion to produce dense point clouds and meshes. Users can work through a graphical interface or command line. The GUI’s automatic reconstruction tool accepts an image folder and creates sparse and dense results in a workspace folder. For development, PyCOLMAP offers Python bindings for most functionality, and COLMAP can be built as a library for C++ code. Feature extraction options include SIFT, ALIKED, and LoMa; ALIKED and LoMa require ONNX support at build time. It supports a range of camera models and multi-camera rigs. Users can install pre-built binaries or build from source; macOS users also have a Homebrew formula, and a pre-built Docker image includes CUDA support. The library uses the new BSD license, while third-party dependencies have separate licenses. The project describes COLMAP as research software that may occasionally exit ungracefully when constraints are not met.

OpenMVG is an open-source C++ library for multiple-view geometry, 3D computer vision, and structure from motion. It provides libraries, binaries, and pipelines for reconstructing 3D scenes from images. Library areas include image manipulation, feature description and matching, feature tracking, camera models, multiple-view geometry, robust estimation, and structure-from-motion algorithms. Its binaries can initialize scenes, detect and match features, perform reconstruction, and export scenes to other multiple-view-stereo frameworks. Those frameworks can compute dense point clouds or textured meshes from exported scenes. OpenMVG is released under the Mozilla Public License 2.0 and is listed as free. The project says it aims to support reproducible research through readable implementations of classic and state-of-the-art algorithms. It is designed for reading, learning, modification, and use, with test-driven development and samples. Tutorials cover data structures, library use, and processing an image dataset. Platforms listed are Windows, macOS, Linux, iOS, Android, and self-hosted, with desktop deployment, API access, point-cloud export, and ground control point support.