Skip to content
Computer Vision and Learning Lab Heidelberg Logo
  • Home
  • People
  • Research
    • Machine Learning
    • Optimization
    • Scene Understanding
    • Natural Science
    • Training Data Generation
  • Publications
  • Teaching & Thesis
  • Events
  • Job Offers
  • Contact
  • Menu
Home » People » Bogdan Savchynskyy » Projects
projects <- back to the main page of Dr. Bogdan Savchynskyy

Running Projects

  • “The Worm” – Unsupervised multi-matching for bio-informatics
  • Scalable max-weight independent set solver
  • Graph matching benchmark
  • Scalable and learnable graph matching solver

Old Projects

  • Scalable and learnable cell tracking in microscopic images
  • 6D Object Pose Estimation
  • Multiple Diverse Solutions in Combinatorial Optimization
  • Scalable Exact and Approximate Inference for Graphical Models and Beyond:
    • Taxonomy of dual block-coordinate ascent methods for MAP-inference in discrete graphical models [pdf] [code] [video-presentation at AISTATS 2020]
    • Exact MAP-Inference by Confining Combinatorial Search with LP Relaxation
    • Parallelizable Approximative Inference for Dense Non-Gaussian Graphical Models
    • knIRPS: Efficient Block-Coordinate Ascent Inference Beyond Graphical Models [code] [paper] [poster]
    • Maximum Persistency in Energy Minimization
    • OpenGM Library and Benchmark for Discrete Energy Minimization
Copyright 2025, Computer Vision and Learning Lab Heidelberg
A SiteOrigin Theme