ASIST: Automatic semantically invariant scene transformation

Or Litany, Tal Remez, Daniel Freedman, Lior Shapira, Alex Bronstein, Ran Gal

Research output: Contribution to journalArticlepeer-review


We present ASIST, a technique for transforming point clouds by replacing objects with their semantically equivalent counterparts. Transformations of this kind have applications in virtual reality, repair of fused scans, and robotics. ASIST is based on a unified formulation of semantic labeling and object replacement; both result from minimizing a single objective. We present numerical tools for the efficient solution of this optimization problem. The method is experimentally assessed on new datasets of both synthetic and real point clouds, and is additionally compared to two recent works on object replacement on data from the corresponding papers.

Original languageEnglish
Pages (from-to)284-299
Number of pages16
JournalComputer Vision and Image Understanding
StatePublished - 1 Apr 2017


  • Alternating minimization
  • Iterative closest point
  • Object recognition
  • Pose estimation
  • Random forest
  • Registration
  • Semantic segmentation

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'ASIST: Automatic semantically invariant scene transformation'. Together they form a unique fingerprint.

Cite this