Can Affordances Guide Object Decomposition into Semantically Meaningful Parts?

Safoura Rezapour Lakani, Antonio Jose Rodríguez-Sánchez, Justus H. PiaterWACV 2017 · OpenReview

Abstract

Most objects are designed for certain functionalities. For example, a knife is designed for cutting, and a hammer for pounding. Indeed, functionalities are not related to the objects themselves but to certain object parts, e.g., the blade of a knife affords cutting. A part can have different shapes and can exist in different objects such as a scraper or a peeler, but it carries the same functional meaning. There is a strong correlation between object parts and affordances. In this paper, we exploit this correlation to decompose objects into semantically meaningful parts. The semantics are limited here to object affordances. We evaluate our method on a part decomposition task, and obtained 77% weighted overlap with ground-truth object parts.
BibTeX
@inproceedings{lakani2017can,
  author = {Safoura Rezapour Lakani and Antonio Jose Rodríguez-Sánchez and Justus H. Piater},
  title = {{Can Affordances Guide Object Decomposition into Semantically Meaningful Parts?}},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year = {2017},
  url = {https://openreview.net/forum?id=eyyRFCb-gGV},
}

Loading related content...

Figure