Chop & Learn: Recognizing and Generating Object-State Compositions

Nirat Saini, Hanyu Wang, Archana Swaminathan, Vinoj Jayasundara, Bo He +2 more
2/14/2026

No official code found. Best implementation: chopnlearn/chopnlearn (4 stars, MIT, last commit 2024-05-31).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

chopnlearn/chopnlearnCommunity62%
MIT

Official Pytorch implementation of the paper: Chop & Learn: Recognizing and Generating Object-State Compositions, ICCV 2023.

40Shell, PythonApr 7, 20242 years agoMIT

Similar Papers

Video State-Changing Object Segmentation

85% match2026

NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks

80% match1 repo1752025

Learning Multiple Object States from Actions via Large Language Models

79% match2024

O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing

79% match2025

ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment

79% match1 repo242025

CAGE: Unsupervised Visual Composition and Animation for Controllable Video Generation

79% match1 repo82024

Cite this paper

@article{saini2026chop,
  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},
  year   = {2026},
  eprint = {2309.14339},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2309.14339},
  journal = {ICCV 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.14339.svg)](https://codeofpaper.com/paper/2309.14339)

Discussion