Awesome

Dissecting Image Crops

This is the official repository for B. Van Hoorick and C. Vondrick, "Dissecting Image Crops," ICCV 2021. In short, we investigate what traces are left behind by visual cropping.

Link to paper on ArXiv

Basic Usage Instructions

Step 1: Populate data/train, data/val, and data/test with high-resolution image files; a constant aspect ratio is strongly preferred.

Step 2: Investigate the command line flags in train.py, and run python train.py with the desired arguments. This will instantiate a new training run with PyTorch checkpoint files in checkpoints/, and TensorBoard log files in logs/.

Step 3: Run python test.py --model_path /path/to/above/checkpoint/folder with relevant arguments to run the model on the test set.

Dataset

In our project, we scraped Flickr based on this script by Sam Lavigne, using each line in google-10000-english-no-swears.txt (see this repository for more info) as search queries. We filtered the photos by an aspect ratio of 1.5, which is the most common value, resulting in a dataset of around 700,000 images. They were captured by diverse (but mostly high-end) camera brands, models, and pipelines.

Known Issues

There is a stubborn memory leak that builds up as you train over many epochs. I have tried many things but do not know how to prevent it.

BibTeX Citation

@article{van2020dissecting,
    title={Dissecting Image Crops},
    author={Van Hoorick, Basile and Vondrick, Carl},
    journal={ICCV 2021},
    year={2020}
}