CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus

Florian Kluger, Eric Brachmann, Hanno Ackermann, Carsten Rother, Michael Ying Yang, Bodo Rosenhahn

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

18 Citations (Scopus)
71 Downloads (Pure)


We present a robust estimator for fitting multiple para-metric models of the same form to noisy measurements. Ap-plications include finding multiple vanishing points in man-made scenes, fitting planes to architectural imagery, or esti-mating multiple rigid motions within the same sequence. In contrast to previous works, which resorted to hand-crafted search strategies for multiple model detection, we learn the search strategy from data. A neural network conditioned on previously detected models guides a RANSAC estima-tor to different subsets of all measurements, thereby finding model instances one after another. We train our method su-pervised as well as self-supervised. For supervised training of the search strategy, we contribute a new dataset for van-ishing point estimation. Leveraging this dataset, the pro-posed algorithm is superior with respect to other robust es-timators as well as to designated vanishing point estimation algorithms. For self-supervised learning of the search, we evaluate the proposed algorithm on multi-homography es-timation and demonstrate an accuracy that is superior to state-of-the-art methods.
Original languageEnglish
Title of host publicationProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Place of PublicationSeattle
Number of pages10
ISBN (Print)978-1-7281-7168-5
Publication statusPublished - 16 Jun 2020
Event33rd IEEE Computer Vision and Pattern Recognition, CVPR 2020 - Virtual Conference
Duration: 14 Jun 202019 Jun 2020
Conference number: 33


Conference33rd IEEE Computer Vision and Pattern Recognition, CVPR 2020
Abbreviated titleCVPR 2020
Internet address


Dive into the research topics of 'CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus'. Together they form a unique fingerprint.

Cite this