Cropper: Vision-Language Model for Image Cropping through In-Context Learning

• Published in: arXiv.org
• Main Authors: Lee, Seung Hyun, Ke, Junjie, Li, Yinxiao, He, Junfeng, Hickson, Steven, Datsenko, Katie, Kim, Sangpil, Ming-Hsuan Yang, Essa, Irfan, Yang, Feng
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 14.08.2024
• Subjects: Aspect ratio; Context; Crops; Free form; Image enhancement; Learning; State-of-the-art reviews; Vision; Visual tasks
• ISSN: 2331-8422

The goal of image cropping is to identify visually appealing crops within an image. Conventional methods rely on specialized architectures trained on specific datasets, which struggle to be adapted to new requirements. Recent breakthroughs in large vision-language models (VLMs) have enabled visual in-context learning without explicit training. However, effective strategies for vision downstream tasks with VLMs remain largely unclear and underexplored. In this paper, we propose an effective approach to leverage VLMs for better image cropping. First, we propose an efficient prompt retrieval mechanism for image cropping to automate the selection of in-context examples. Second, we introduce an iterative refinement strategy to iteratively enhance the predicted crops. The proposed framework, named Cropper, is applicable to a wide range of cropping tasks, including free-form cropping, subject-aware cropping, and aspect ratio-aware cropping. Extensive experiments and a user study demonstrate that Cropper significantly outperforms state-of-the-art methods across several benchmarks.