Back to browse
GitHub Repository
0 starsJupyter Notebook

Incremental SfM pipeline that reconstructs 3D point clouds from images

by egeozgul·Jun 6, 2026·1 point·0 comments

AI Analysis

●●SolidBig BrainNiche Gem

Working SfM pipeline from scratch, but COLMAP already does this at production scale.

Strengths
  • Full pipeline from SIFT matching through triangulation with RANSAC outlier rejection
  • Jupyter notebook walkthrough makes the math and implementation accessible
  • Real dataset with Maiden's Tower photos demonstrates orbit coverage requirements
Weaknesses
  • No novel techniques beyond standard OpenCV photogrammetry workflows
  • Zero stars, no documentation beyond the README, unclear maintenance plans
Category
Target Audience

Computer vision developers, students learning photogrammetry

Similar To

COLMAP · OpenMVG · AliceVision

Post Description

Built an incremental Structure from Motion pipeline that reconstructs a sparse 3D point cloud from a sequence of images. Used Kız Kulesi (Maiden's Tower) in Istanbul as the demo dataset. Interactive 3D viewer included.

Similar Projects

Developer Tools●●Solid

Photon – Rust pipeline that embeds/tags/hashes images locally w SigLIP

Local SigLIP embeddings + 68K-term semantic tagging in a single Rust binary, zero cloud.

WizardryNiche GemShip It
pgbouncer
313mo ago