Skip to content
SPECIFICTION
Get listed

OpenReco

abhibagul.github.io

Free plan Open source WebWindowsmacOSLinuxAPISelf-hosted
Visit abhibagul.github.io
Spec score 8.6 #5 of 34 in Photogrammetry Software

What it is

OpenReco converts drone and camera imagery into dense point clouds, textured meshes, orthomosaics, and elevation models. Its node-based workspace can run a complete reconstruction graph or individual stages, while caching keeps results reproducible. Reconstruction uses COLMAP CUDA for GPU multi-view stereo and includes an automatic CPU fallback. Models can be georeferenced from EXIF GPS data or ground control points. Analysis tools measure volume, profile, area, and distance, and generate NDVI, ExG, and VARI vegetation maps. Listed exports include LAS, LAZ, PLY, OBJ, GeoTIFF, GeoJSON, DXF, CSV, 3D Tiles, and contour SHP. OpenReco is MIT licensed and open source. Desktop downloads are listed for Windows, macOS, and Linux. The site says no account or subscription is needed to download it, and the Free plan is free. Named target fields include surveying and mapping, agriculture and forestry, VFX and heritage, construction and earthworks, and robotics and research.

Spec sheet

What it does
OpenReco converts drone or camera photographs into georeferenced dense point clouds, textured meshes, orthomosaics and elevation models.Read 15 Oct 2026 · abhibagul.github.io
License
The site describes OpenReco as MIT licensed and open source.Read 4 Oct 2026 · abhibagul.github.io
Maker
The GitHub account identifies the maker as Abhishek Bagul, a full-stack web developer based in India.Read 15 Oct 2026 · github.com
Account and subscription
The site says users can download OpenReco with no account and no subscription.Read 4 Oct 2026 · abhibagul.github.io
Analysis
Features include volume, profile, area, and distance measurements, plus NDVI, ExG, and VARI vegetation maps.Read 4 Oct 2026 · abhibagul.github.io
CLI
The command line includes run, resume, diff, report, stages, batch, export, ui, volume and profile commands.Read 15 Oct 2026 · github.com
Dense reconstruction
Dense multi-view stereo depth maps are fused into a high-density point cloud, using COLMAP CUDA with CPU fallback.Read 15 Oct 2026 · abhibagul.github.io
Desktop UI
The UI provides a layer tree, schema-driven parameter panels, live run progress and a three.js 3D viewport.Read 15 Oct 2026 · github.com
Documentation depth
The repository contains documentation covering discovery, product planning, architecture, pipeline specification and roadmap, plus a detailed README.Read 15 Oct 2026 · github.com
Download platforms
The site lists Windows, macOS, and Linux downloads.Read 4 Oct 2026 · abhibagul.github.io
Elevation products
The product can rasterize digital surface models and generate contours from elevation data.Read 15 Oct 2026 · abhibagul.github.io
Export formats
Listed outputs include LAS, LAZ, PLY, OBJ, GeoTIFF, GeoJSON, DXF, CSV, 3D Tiles and contour shapefiles.Read 15 Oct 2026 · abhibagul.github.io
Exports
Listed output formats include LAS, LAZ, PLY, OBJ, GeoTIFF, GeoJSON, DXF, CSV, 3D Tiles, and contour SHP.Read 4 Oct 2026 · abhibagul.github.io
Georeferencing
Models can be positioned using EXIF GPS or ground-control points in an EPSG coordinate reference system.Read 15 Oct 2026 · abhibagul.github.io
GPU requirements
NVIDIA dense processing requires the machine's NVIDIA driver and CUDA COLMAP; macOS uses CPU because it has no CUDA.Read 15 Oct 2026 · github.com
Install options
The README describes standalone PyInstaller binaries plus installation from Python with pip and an optional bootstrap command.Read 15 Oct 2026 · github.com
Licence
OpenReco is released under the MIT licence and its stated dependencies are restricted to permissive BSD, MIT, Apache or similar licences.Read 15 Oct 2026 · github.com
Limit: approximate outputs
Orthophoto processing is described as approximate and the DTM is based on morphological DSM processing.Read 15 Oct 2026 · github.com
Limit: Gaussian splatting
The Gaussian Splatting branch requires torch, gsplat, CUDA, nvcc, CUDA headers and a host C++ compiler, and is not validated on the developer's Windows machine.Read 15 Oct 2026 · github.com
Limit: maturity
The README labels the project an incomplete v0.1.1 release and describes it as early even though the UAV pipeline is functional.Read 15 Oct 2026 · github.com
Limit: missing capabilities
Multi-image texture blending, PBR, cloud collaboration, learned matching, USD/COPC/3D-Tiles streaming and full GUI collaboration are listed as not yet built or roadmap work.Read 15 Oct 2026 · github.com
Maker background
The maker's profile says he previously worked as an aerial surveyor for three years.Read 15 Oct 2026 · github.com
Measurements
Users can calculate cut/fill volume, elevation profiles, areas and distances directly on the model.Read 15 Oct 2026 · abhibagul.github.io
Mesh generation
OpenReco reconstructs polygonal surfaces with Poisson meshing and can produce models with millions of vertices.Read 15 Oct 2026 · abhibagul.github.io
Neural extension
An experimental 3D Gaussian Splatting stage trains from the SfM camera solution and exports a 3DGS PLY file.Read 15 Oct 2026 · github.com
Orthomosaics
It produces orthorectified, georeferenced image mosaics intended for GIS use.Read 15 Oct 2026 · abhibagul.github.io
Photo alignment
The alignment stage detects and matches features and solves camera poses for a sparse point cloud.Read 15 Oct 2026 · abhibagul.github.io
Point classification
A classification stage is listed for separating ground, building and vegetation points.Read 15 Oct 2026 · abhibagul.github.io
Python API
The Python API exposes Project open/run operations, stage metrics, reports and volume measurement.Read 15 Oct 2026 · github.com
Python requirement
The package metadata requires Python 3.11 or newer and has no mandatory runtime dependencies in its base phase.Read 15 Oct 2026 · github.com
Reconstruction
The product uses COLMAP CUDA for GPU multi-view stereo and says it has an automatic CPU fallback.Read 4 Oct 2026 · abhibagul.github.io
Reproducibility
Stage cache keys are derived from inputs and resolved parameters so unchanged stages can be reused byte-for-byte.Read 15 Oct 2026 · abhibagul.github.io
Self-hosting
The software is local-first and can produce a self-contained output folder that can be hosted statically without a server.Read 15 Oct 2026 · github.com
SourceForge downloads
SourceForge showed 7 downloads in the week displayed and a last update date of 2026-08-03.Read 15 Oct 2026 · sourceforge.net
SourceForge licence
SourceForge identifies the project licence as MIT.Read 15 Oct 2026 · sourceforge.net
SourceForge operating systems
SourceForge lists Linux, Mac and Windows as supported operating systems.Read 15 Oct 2026 · sourceforge.net
SourceForge planned features
SourceForge marks orthomosaic and DEM workflows and an extensible plugin architecture as planned features.Read 15 Oct 2026 · sourceforge.net
SourceForge registration
SourceForge records the project as registered on 2026-06-20.Read 15 Oct 2026 · sourceforge.net
SourceForge review coverage
The SourceForge page invites users to post the first review, so it displays no user-review rating or review count.Read 15 Oct 2026 · sourceforge.net
System requirements
The standalone builds target Windows x64, macOS ARM64 and Linux with recent glibc such as Ubuntu 22.04+.Read 15 Oct 2026 · github.com
Target users
The site names surveying and mapping, agriculture and forestry, VFX and heritage, construction and earthworks, and robotics and research as target fields.Read 4 Oct 2026 · abhibagul.github.io
Texturing
The texturing stage bakes a UV atlas from registered source imagery.Read 15 Oct 2026 · abhibagul.github.io
Vegetation indices
NDVI, ExG and VARI maps are listed for agriculture and forestry analysis.Read 15 Oct 2026 · abhibagul.github.io
Visualization
The viewport supports RGB or elevation coloring, scientific colormaps, eye-dome lighting and model, orthographic, map and photo views.Read 15 Oct 2026 · abhibagul.github.io
Workflow
Its node-based workspace can run the complete reconstruction graph or individual stages, with cached reproducible results.Read 15 Oct 2026 · abhibagul.github.io

Plans and prices

Free Free No account · no subscription · Windows, macOS and Linux downloads Read 15 Oct 2026 · abhibagul.github.io

Every OpenReco plan and price →

Strong points and limits

Strong points

  • Runs on Windows, macOS, and Linux
  • GPU processing with automatic CPU fallback
  • Supports EXIF GPS and ground control points
  • Broad 3D, GIS, and measurement exports
  • No account or subscription required

Limits

  • Desktop software only
  • Processing depends on imagery and reconstruction workflow
  • No hosted deployment option is listed

Who it suits

OpenReco suits professionals and researchers in surveying, mapping, agriculture, forestry, VFX, heritage, construction, earthworks, and robotics.

Verdict

OpenReco provides an open-source desktop pipeline from imagery through reconstruction, georeferencing, analysis, and export. Its many output formats and CPU fallback support varied workflows, while users manage the desktop installation themselves.

Where Specifiction places it

Alternatives to OpenRecoAll alternatives →