The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs

Chris Rockwell, Justin Johnson, David F. Fouhey

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a simple baseline for directly estimating the relative pose (rotation and translation, including scale) between two images. Deep methods have recently shown strong progress but often require complex or multi-stage architectures. We show that a handful of modifications can be applied to a Vision Transformer (ViT) to bring its computations close to the Eight-Point Algorithm. This inductive bias enables a simple method to be competitive in multiple settings, often substantially improving over the state of the art with strong performance gains in limited data regimes.

Original languageEnglish (US)
Title of host publicationProceedings - 2022 International Conference on 3D Vision, 3DV 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages155-165
Number of pages11
ISBN (Electronic)9781665456708
DOIs
StatePublished - 2022
Event10th International Conference on 3D Vision, 3DV 2022 - Prague, Czech Republic
Duration: Sep 12 2022Sep 15 2022

Publication series

NameProceedings - 2022 International Conference on 3D Vision, 3DV 2022

Conference

Conference10th International Conference on 3D Vision, 3DV 2022
Country/TerritoryCzech Republic
CityPrague
Period9/12/229/15/22

Keywords

  • Camera Pose
  • Eight Point Algorithm
  • Vision Transformer

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs'. Together they form a unique fingerprint.

Cite this