Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
PanorAi documentation
PanorAi documentation
  • Quick start
  • Guides
    • The four API levels
      • Applications: solve the task first
      • Pipeline: compose the method
      • Spherical Ops: control the operation
      • Geometry: control rays and projections
    • Process and project panoramic images
    • Extract and match visual features
    • Estimate pose, depth and radial range
    • Registration and panorama stitching
    • Localize and associate semantic regions
    • Composed spherical API
    • Detailed tutorials
      • Compose a sphere-native model
      • Quick start
      • Work with a spherical image object
      • Projection foundations: sphere, rays, views, samplers, and blenders
      • Cubemap, batch, and autograd
      • Tutorial: image processing on the sphere
      • Clean spherical masks with morphology
      • Tutorial: spherical features and matching
      • Tutorial: spherical Essential matrix and two-view triangulation
      • Tutorial: dense stereo from two spherical images
      • Tutorial: resize-free spherical monocular depth
      • Tutorial: from matched panoramas to a multiview reconstruction
      • Tutorial: spherical visual SLAM
      • Tutorial: pretrained spherical FCN and class-activation maps
      • From spherical CAMs to spatial object hypotheses
      • How PanorAi executes computer vision on spherical images
      • Tutorial: benchmark speed and geometric accuracy
    • How-to guides
      • Choose modality, layout, and interpolation
      • Preprocessing Containers
      • Spherical image processing
      • Spherical features and matching
      • Analyze regions on a sphere
      • Evaluate spherical results reproducibly
      • Build and query a spatial-semantic graph
      • Estimate spherical pose and reconstruct multiple panoramas
      • Run spherical visual SLAM
    • Apply a pinhole method over the sphere
    • Choose sampling and fusion
    • Return the right spherical output
    • Extract and match spherical features
    • How projected features become spherical observations
    • Detect features directly on the sphere
    • Match features and inspect the evidence
    • Estimate relative pose
    • Recover metric scale and triangulate
    • Run panoramic dense stereo from two ERPs
    • Reconstruct a surface from registered spherical views
    • Estimate dense range with spherical stereo
    • Compare non-learned stereo pipelines
    • Choose a monocular range strategy
    • Port Metric3D directly to the sphere
    • Run Depth Anything over tangent views
    • Validate and consume radial range
    • Generate a CAM with a pretrained spherical CNN
    • Interpret a spherical CAM
    • Convert CAM evidence into angular proposals
    • Associate proposals across registered views
    • Refine an accepted region with local masks
    • Evaluate semantic regions and hypotheses
  • Concepts
    • Application wrappers
    • Typed pipeline composition
    • Sphere-aware operations
    • Spherical morphology
    • Spherical region analysis
    • Spherical research evaluation
    • Registration and stitching
    • The geometry contract
    • The spherical image object
    • PanorAi canonical spherical geometry
    • Architecture
    • Ergonomic workflow evolution
    • Related libraries and PanorAi’s role
    • Direct spherical dense stereo: geometry and optimization
    • Spherical dense reconstruction
    • Spherical frontend v2 promotion plan
  • API reference
    • Component catalog
      • Applications catalog
      • Pipeline Stages catalog
      • Spherical Ops and layers catalog
      • Estimators and policies catalog
      • Typed data and results catalog
      • Geometry catalog
      • Research evaluation catalog
      • Subsystems and advanced surfaces
      • Complete public-surface inventory
    • Applications API
    • EquirectangularImage API
    • Pipeline API
    • Spherical operations API
    • Canonical geometry API
    • Composable spherical operations
    • Spherical raster fields and observations
    • Spherical feature API
    • Spherical relative-pose API
    • Calibration API
    • Model-fitting API
    • Registration and stitching API
    • Spherical evaluation API
    • Spatial-semantic graph API
    • Semantic object association and localization
    • Global spherical reconstruction
    • Stereo APIs
    • Spherical visual SLAM
    • Optional depth adapters
    • Projectors
    • Sampling and fusion methods
    • Capabilities
    • API stability in 3.x
  • Development
    • Public roadmap
    • Computer-vision research capability roadmap
    • Adding a public API component
    • Spherical application promotion protocol
    • Governance
    • Evidence
    • Benchmarks and performance
    • Planned 4.0 destination map
    • Development history
  • Releases
    • PanorAi 3.8.0 release checklist
    • PanorAi 3.7.0 release checklist
    • PanorAi 3.6.0 release checklist
    • PanorAi 3.5.0 release checklist
    • PanorAi 3.4.0 release checklist
    • PanorAi 3.3.1 release checklist
    • PanorAi 3.3.0 release checklist
    • PanorAi 3.2.0 release checklist
    • PanorAi 3.1.0 release checklist
    • Migrating from PanorAi 3.0.19 to 3.1.0
    • Composed spherical API migration
  • Methodology manuscript
Back to top
View this page

How-to guides¶

  • Choose modality, layout, and interpolation
  • Preprocessing Containers
  • Spherical image processing
  • Spherical features and matching
  • Analyze regions on a sphere
  • Evaluate spherical results reproducibly
  • Build and query a spatial-semantic graph
  • Estimate spherical pose and reconstruct multiple panoramas
  • Run spherical visual SLAM
Next
Choose modality, layout, and interpolation
Previous
Tutorial: benchmark speed and geometric accuracy
Copyright ©
Made with Sphinx and @pradyunsg's Furo