Releases: alicevision/Meshroom
Meshroom 2025.1.0 (2025/08/18)
Meshroom has now become a node-based visual programming toolbox for creating, managing, and executing complex data processing pipelines, with a new plugin architecture.
Standard computer vision pipelines such as photogrammetry, camera tracking, HDR panorama, Lidar Meshing, Raw image files conversion and color calibration are now unified within the AliceVision plugin, featuring numerous improvements and optimizations.
Additionally, new AI-powered capabilities include a semantic segmentation plugin and a collection of open-source extensions available via the new MeshroomHub: https://github.com/meshroomHub. This platform enables Gaussian Splatting, monocular depth estimation, and other exploratory features, welcoming developer contributions to expand and enhance these capabilities for upcoming releases.
Download
Download Meshroom-2025.1.0 for Linux
Download Meshroom-2025.1.0 for Windows
Highlights
Meshroom New Features
- Advanced Plugin Architecture: Dedicated sub-process isolation for Python nodes with independent local environments
- Integrated Development Tools:
- Built-in Python script editor
- Node’s source code hot-reload for rapid node development iterations
- Enhanced GraphEditor:
- Dynamic output attributes enabling new workflow usages
- New InputNode type enabling interactive evaluation without explicit computation
- Multiple edge disconnection methods and node colorization for better user experience
- Node notifications to attribute changes
- Enhanced 2D Viewer:
- Initial timeline integration with sequence playback controls
- New Reflectance Transformation Imaging (RTI) Viewer: Interactive visualization of albedo and normal maps with real-time lighting control
- New Home Page: featuring pipeline templates and quick access to recent projects.
AliceVision Plugin New Features
- New Pipelines
- Color Calibration: Automated color correction from color charts
- Raw to EXR conversion: Professional image format processing
- Object Reconstruction: Targeted reconstruction with automatic object segmentation
- Turntable Object Reconstruction: Streamlined workflow for rotating object capture
- 360° Object Reconstruction: Reconstruction of complete dual-sided scanning
- LiDAR Processing: Native E57 file import with integrated mesh generation
- Multi-View Photometric Stereo: Advanced surface detail reconstruction with multiple light sources for each viewpoint.
- Pipelines Improvements
- Camera Tracking pipeline: improved stability and reliability
- Introduced experimental fine-grained pipelines for increased modularity and workflow flexibility
- Core Enhancements
- Python Bindings Integration: Enhanced AliceVision accessibility with native Python support for streamlined Machine Learning workflows
New MrSegmentation Plugin
AI segmentation nodes that identify and isolate image objects using natural language prompts, enabling intuitive content-aware processing through foundation models.
MeshroomHub Plugins
We're excited to introduce new experimental Machine Learning plugins available on MeshroomHub.
These plugins showcase the future of Meshroom workflows, though they currently require developer setup and cannot be installed through the user interface yet.
- mrGSplat: Gaussian Splat optimization and rendering
- mrDepthEstimation: Monocular depth inference
- mrDenseMotion: Optical flow estimation
- mrRoma: Dense deep feature matching
- mrIntrinsicImageDecomposition: Albedo, normals, and material extraction
- mrDeblurring: Video deblurring
- mrGeolocation: GPS extraction and geographic models download
Based on AliceVision 3.3.0.
Major Features
- Add an "E57" importer node PR
- First node for Lidar Meshing PR
- New InputNode for nodes without computation and support for all param types in output (and no more limited to File type) PR
- [core] New dynamic output attributes PR
- First Homepage PR
- Qt6.6.3 / PySide6.6.3.1 upgrade PR
- New MultiView Photometric Stereo pipeline and new sfmFilter node PR
- [ui] Python Script Editor Improvements PR
- New local isolated computation for python nodes PR
- New Plugin Architecture for Node Registration PR
- [ui]: Introduction of multiple ways to remove Node Edges PR
- [core] Runtime-specific environments support PR
- [Photometric Stereo] MultiView fusion in Texturing PR
- Add a Python ScriptEditor in the GraphEditor tab PR
Features
- Custom loader for .pc.ply point clouds PR
- Lidar nodes PR
- [ui] Viewer2D: Display lighting circle with auto detected sphere PR
- [ui] RGBA shortcuts for Image Viewer PR
- [ui] Shortcuts in Viewer2D and SequencePlayer PR
- [ui] node time computation and chunks count in node editor header PR
- [core/ui] Load image sequence from node's output in SequencePlayer PR
- [core] Forward the onAttributeChanged notification to all linked attributes PR
- add 3de undistortion models PR
- [GraphEditor] Base
ChoiceParam
model on attribute instead of description PR - [core] Reference the attribute's instance type in its description PR
- [ui] Improve command line help message PR
- Added Pre and Post process functions on the Base Node PR
- [ui] Add and improve multiple UI tools for Photometric stereo PR
- Refactor Node selection for better UX and performance PR
- New SfMColorizing Node PR
- Update sfm pipeline to accept meshes PR
- Enable Fitting of selected Nodes in the Graph Editor when Fit is invoked PR
- Add relative paths to nodes as variables PR
- Node to inject survey points in the SFM PR
- [ui] AttributeEditor: Feature/attribute navigation buttons PR
- [ui] Homepage: Project can be removed with right click PR
- [ui] Viewer2D: Add the pixel (x,y) values in the toolbar (editable) PR
- [ui] AttributeEditor: Allow displaying attibute in corresponding viewport PR
- Update to Qt/PySide 6.8.3 PR
- Add a "ConvertDistortion" node PR
- [ui] Sync SequencePlayer and Viewer3D PR
- Viewer3D: Adjust bounding-box by moving faces PR
- [core/ui] Add support for PushButton attribute PR
- First version of For Loop implementation PR
- Generate depthmaps from sfmData and mesh PR
- [ui] Use the improved Sequence Player and enable it by default PR
- [AttributePin] Add tooltip to display type of attribute PR
- [core/ui] "Exposed" property added to attributeDesc PR
- Extract more metadata using exifTool PR
- Add equirectangular camera model in
CameraInit
PR - Fix: Improve large project file loading performance PR
- UI: Redesign ChoiceParam UI component PR
- Create new pipeline for testing modular sfm PR
- [ui] Graph Editor Update: Quick Node Coloring with the Color Selector Tool PR
- [doc] README.md: Add DeepWiki link, the AI documentation you can talk to [PR](https://githu...
Meshroom 2023.3.0 (2023/12/07)
Download
Prebuilt binaries on this page are all-in-one packages including AliceVision and all required resources.
To start the application, unzip the archive and launch the Meshroom
executable.
To fully utilize Meshroom, a NVIDIA CUDA-enabled GPU is recommended. The binaries are built with CUDA-11 and are compatible with compute capability >= 3.5. Without a supported NVIDIA GPU, only "Draft Meshing" can be used for 3D reconstruction.
NVIDIA CUDA Installation Guide for Linux
MacOS: Unfortunately there is no official MacOS release. Here you can read more about the topic.
Release Notes Summary
- New node for semantic image segmentation PR
- Support pixel aspect ratio (no UI) PR
- Noise reduction in HDR merging PR
- [ui] 2D viewer: image sequence player PR
- [bin] meshroom_batch: support multiple init nodes PR
- [nodes] StructureFromMotion: Automatic alignment of the 3D reconstruction PR
- New node for intrinsics and rig calibration using a multiview acquisition of a checkerboard PR
- New Nodal Camera Tracking pipeline PR
- Manage LCP in imageProcessing PR
- [Viewer3D] Add slider to display cameras based on their resection IDs PR
Full Release Notes: https://github.com/alicevision/meshroom/blob/v2023.3.0/CHANGES.md
Based on AliceVision 3.2.0.
Meshroom 2023.2.0 (2023/06/26)
Download
Prebuilt binaries on this page are all-in-one packages including AliceVision and all required resources.
To start the application, unzip the archive and launch the Meshroom
executable.
To fully utilize Meshroom, a NVIDIA CUDA-enabled GPU is recommended. The binaries are built with CUDA-11 and are compatible with compute capability >= 3.5. Without a supported NVIDIA GPU, only "Draft Meshing" can be used for 3D reconstruction.
NVIDIA CUDA Installation Guide for Linux
MacOS: Unfortunately there is no official MacOS release. Here you can read more about the topic.
Release Notes Summary
- New Photometric Stereo nodes PR
- [nodes] New CheckerboardDetection node PR
- [nodes] Split360Images: Add support for SfMData file as input and output PR
- [sfmTransform] Add an auto mode PR
- [nodes] DepthMap: New option for multi-resolution similarity estimation and optimizations PR
- [nodes] Distortion calibration PR
- Add a template for the HDR fusion PR
- [pipelines] New CameraTracking pipeline PR
- [pipelines] New "Photogrammetry and Camera Tracking" pipeline PR
Full Release Notes: https://github.com/alicevision/meshroom/blob/v2023.2.0/CHANGES.md
Based on AliceVision 3.1.0.
Meshroom 2023.1.0 (2023/03/22)
Download
Prebuilt binaries on this page are all-in-one packages including AliceVision and all required resources.
To start the application, unzip the archive and launch Meshroom
executable.
To fully utilize Meshroom, a NVIDIA CUDA-enabled GPU is recommended. The binaries are built with CUDA-11 and are compatible with compute capability >= 3.5. Without a supported NVIDIA GPU only "Draft Meshing" can be used for 3D reconstruction.
NVIDIA CUDA Installation Guide for Linux
MacOS: Unfortunately there is no official MacOS release. Here you can read more about the topic.
Release Notes Summary
- Major improvements of the depth map quality, performances and scalability. The full resolution can now be computed on most of the standard GPUs.
- FeatureExtraction is now using DSP-SIFT by default for the 3D Reconstruction pipeline.
- Capacity to create panoramas with very high resolutions using a limited amount of memory.
- Enhanced interpretation of RAW images, including new support for Adobe Digital Camera Profile and Lens Camera Profiles databases (if installed on your workstation).
- Improved color management with OCIO support and more options to export in various colorspaces including ACEScg.
- New graph templates enabling users to create custom pipelines.
- Expose a new experimental pipeline for Camera Tracking.
- Improved GraphEditor with copy-paste and multi-selection.
- Improved ImageGallery with thumbnails cache and search options.
- 2D Viewer is now using floating-point images by default.
- And a very large amount of UI improvements and bug fixes.
Full Release Notes: https://github.com/alicevision/meshroom/blob/v2023.1.0/CHANGES.md
Based on AliceVision 3.0.0.
Release 2021.1.0 (2021/02/26)
Download
Prebuilt binaries on this page are all-in-one packages including AliceVision and all required resources.
To start the application, unzip the archive and launch Meshroom
executable.
To fully utilize Meshroom, a NVIDIA CUDA-enabled GPU is recommended. The binaries are built with CUDA-10 and are compatible with compute capability 3.0 to 7.5. Without a supported NVIDIA GPU only "Draft Meshing" can be used for 3D reconstruction.
NVIDIA CUDA Installation Guide for Linux
MD5 Checksums for Linux and Windows binaries
Meshroom-2021.1.0-linux-cuda10.tar.gz: D63C0829531307109E2600DEBF183A34Meshroom-2021.1.0-win64.zip: 12253B9E3A105A72745CD0306500E1FC
MacOS: Unfortunately there is no official MacOS release. Here you can read more about the topic.
Release Notes Summary
- [panorama] PanoramaCompositing: new algorithm with tiles to deal with large panoramas PR
- [feature] Improve robustness of sift features extraction on challenging images: update default values, add new filtering and add dsp-sift variation PR
- [ui] Improve Graph Editor UX with better visualization of nodes connections, the ability to accumulate nodes to compute locally or the ability to compute multiple branches in parallel on renderfarm with a new locking system per node, etc. PR
- [nodes] Meshing: improve mesh quality with a new post-processing. Cells empty/full status are filtered by solid angle ratio to favor smoothness. PR
- [nodes] MeshFiltering: smoothing & filtering on subset of the geometry PR
- [ui] Viewer: fix gain/gamma behavior and use non-linear sliders PR
Full Release Notes: https://github.com/alicevision/meshroom/blob/v2021.1.0/CHANGES.md
Meshroom 2020.1.1 (2020/10/14)
Download
Meshroom-2020.1.0 for Linux
Meshroom-2020.1.1 for Windows
Prebuilt binaries on this page are all-in-one packages including AliceVision and all required resources.
To start the application, unzip the archive and launch Meshroom
executable.
Note: The release 2020.1.1 fixes an instability of the release 2020.1.0 on Windows.
Requirement: NVIDIA CUDA-enabled GPU (built with CUDA-10 compatible with compute capability 3.0 to 7.5).
Release Notes Summary
- [nodes] New Panorama Stitching nodes with support for fisheye lenses PR PR
- [nodes] HDR: Largely improved HDR calibration, including new LdrToHdrSampling for optimal sample selection PR PR PR
- [ui] Viewer3D: Input bounding box (Meshing) & manual transformation (SfMTransform) thanks to a new 3D Gizmo PR
- [ui] Sync 3D camera with image selection PR
- [ui] New HDR (floating point) Image Viewer PR
- [ui] Ability to load depth maps into 2D and 3D Viewers PR PR
- [ui] New features overlay in Viewer2D allows to display tracks and landmarks PR PR
- [ui] Add SfM statistics PR
- [ui] Visual interface for node resources usage PR
- [nodes] Coordinate system alignment to specific markers or between scenes PR
- [nodes] New Sketchfab upload node PR
- [ui] Dynamic Parameters: add a new 'enabled' property to node's attributes PR PR
- [ui] Viewer: add Camera Response Function display PR PR
- [ui] UI improvements in the Viewer2D and ImageGallery PR
- [bin] Improve Meshroom command line PR PR
- [nodes] New ImageProcessing node PR PR PR
- [nodes]
FeatureMatching
Addfundamental_with_distortion
option PR - [multiview] Declare more recognized image file extensions PR
- [multiview] More generic metadata support PR
Full Release Notes: https://github.com/alicevision/meshroom/blob/v2020.1.1/CHANGES.md
Meshroom 2019.2.0 (2019/08/08)
Download
Meshroom-2019.2.0 for Linux
Meshroom-2019.2.0 for Windows
Prebuilt binaries on this page are all-in-one packages including AliceVision and all required resources.
To start the application, unzip the archive and launch Meshroom
executable.
Requirement: NVIDIA CUDA-enabled GPU (compute capability >= 2.0).
Warning: The Linux binaries have been updated on 2019-08-23 to fix a compatibility issue: #594 with a new build based on cuda-7.0 and some libraries updates.
Release Notes Summary
- Visualization: New visualization module of the features extraction. PR, New QtAliceVision
- Support for RAW image files.
- Texturing: Largely improve the Texturing quality.
- Texturing: Speed improvements.
- Texturing: Add support for UDIM.
- Meshing: Export the dense point cloud in Alembic.
- Meshing: New option to export the full raw dense point cloud (with all 3D points candidates before cut and filtering).
- Meshing: Adds an option to export color data per vertex and MeshFiltering correctly preserves colors.
Based on AliceVision 2.2.0.
See Changelog for more details.
Meshroom 2019.1.0 (2019/02/27)
Download
Meshroom-2019.1.0 for Linux
Meshroom-2019.1.0 for Windows
Prebuilt binaries on this page are all-in-one packages including AliceVision and all required resources.
To start the application, unzip the archive and launch Meshroom
executable.
A video overview of Meshroom is available here.
Requirement: NVIDIA CUDA-enabled GPU (compute capability >= 2.0).
Linux: on some distributions (e.g Ubuntu), you may have conflicts between native drivers and mesa drivers, resulting in an empty black window. In that case, you need to force usage of native drivers by adding them to the LD_LIBRARY_PATH: LD_LIBRARY_PATH=/usr/lib/nvidia-340 ./Meshroom
You may need to adjust the folder /usr/lib/nvidia-340 with the correct driver version.
Release Notes Summary
- 3D Viewer: Load and compare multiple assets with cache mechanism and improved navigation
- Display camera intrinsic information extracted from metadata analysis
- Easier access to a more complete sensor database with a more reliable camera model matching algorithm.
- Attribute Editor: Hide advanced/experimental parameters by default to improve readability and simplify access to the most useful, high-level settings. Advanced users can still enable them to have full access to internal thresholds.
- Graph Editor: Improved set of contextual tools with
duplicate
/remove
/delete data
actions withFrom Here
option. - Nodes: Homogenization of inputs / outputs parameters
- Meshing: Better, faster and configurable estimation of the space to reconstruct based on the sparse point cloud (new option
estimateSpaceFromSfM
). Favors high-density areas and helps removing badly defined ones. - Draft Meshing (no CUDA required): the result of the sparse reconstruction can now be directly meshed to get a 3D model preview without computing the depth maps.
- MeshFiltering: Now keeps all reconstructed parts by default.
- StructureFromMotion: Add support for rig of cameras
- Support for reconstruction with projected light patterns and texturing with another set of images
Based on AliceVision 2.1.0.
See Changelog for more details.
Meshroom 2018.1.0 (2018/08/09)
First release of Meshroom, based on AliceVision 2.0.0.
Prebuilt binaries on this page are all-in-one packages including AliceVision and all required resources.
To start the application, unzip the archive and launch Meshroom
executable.
A video overview of Meshroom is available here.
Requirement: NVIDIA CUDA-enabled GPU (compute capability >= 2.0).
Update for Windows 7 Users: Meshroom-2018.1.0-win7-64.zip contains the fix regarding the multi-threading issue #183 that prevented some processes to finish correctly. Please use this version if working on this OS.
Linux: on some distributions (e.g Ubuntu), you may have conflicts between native drivers and mesa drivers, resulting in an empty black window. In that case, you need to force usage of native drivers by adding them to the LD_LIBRARY_PATH: LD_LIBRARY_PATH=/usr/lib/nvidia-340 ./Meshroom
You may need to adjust the folder /usr/lib/nvidia-340 with the correct driver version.
See Changelog for more details.