Model-based invariants for 3-D vision

Daphna Weinshall*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

61 Scopus citations


Invariance under a group of 3-D transformations seems a desirable component of an efficient 3-D shape representation. We propose representations which are invariant under weak perspective to either rigid or linear 3-D transformations, and we show how they can be computed efficiently from a sequence of images with a linear and incremental algorithm. We show simulated results with perspective projection and noise, and the results of model acquisition from a real sequence of images. The use of linear computation, together with the integration through time of invariant representations, offers improved robustness and stability. Using these invariant representations, we derive model-based projective invariant functions of general 3-D objects. We discuss the use of the model-based invariants with existing recognition strategies: alignment without transformation, and constant time indexing from 2-D images of general 3-D objects.

Original languageAmerican English
Pages (from-to)27-42
Number of pages16
JournalInternational Journal of Computer Vision
Issue number1
StatePublished - Feb 1993
Externally publishedYes


Dive into the research topics of 'Model-based invariants for 3-D vision'. Together they form a unique fingerprint.

Cite this