Recognizing and generating object-state compositions has been a challenging task, especially when generalizing to unseen compositions. In this paper, we study the task of cutting objects in different styles and the resulting object state changes. We propose a new benchmark suite Chop & Learn, to accommodate the needs of learning objects and different cut styles using multiple viewpoints. We also propose a new task of Compositional Image Generation, which can transfer learned cut styles to different objects, by generating novel object-state images. Moreover, we also use the videos for Compositional Action Recognition, and show valuable uses of this dataset for multiple video tasks. Project website: https://chopnlearn.github.io.
@article{arxiv.2309.14339,
title = {Chop & Learn: Recognizing and Generating Object-State Compositions},
author = {Nirat Saini and Hanyu Wang and Archana Swaminathan and Vinoj Jayasundara and Bo He and Kamal Gupta and Abhinav Shrivastava},
journal= {arXiv preprint arXiv:2309.14339},
year = {2023}
}