Deep Feature Interpolation for Image Content Changes

November 16, 2016 ยท Entered Twilight ยท ๐Ÿ› Computer Vision and Pattern Recognition

๐ŸŒ… TWILIGHT: Old Age
Predates the code-sharing era โ€” a pioneer of its time

"Last commit was 8.0 years ago (โ‰ฅ5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE, README.md, alignface.py, dataset_rebuild.py, datasets, deepart.py, deepmodels.py, deepmodels_torch.py, demo1.py, demo2.py, demo3.py, documentation, facemodel_server.py, facemodel_worker.py, images, imageutils.py, interface.py, models, npz.py, render_movie.py, results, tests, torch_models.py, totalvariation.py, utils.py

Authors Paul Upchurch, Jacob Gardner, Geoff Pleiss, Robert Pless, Noah Snavely, Kavita Bala, Kilian Weinberger arXiv ID 1611.05507 Category cs.CV: Computer Vision Citations 327 Venue Computer Vision and Pattern Recognition Repository https://github.com/paulu/deepfeatinterp โญ 276 Last Checked 1 month ago
Abstract
We propose Deep Feature Interpolation (DFI), a new data-driven baseline for automatic high-resolution image transformation. As the name suggests, it relies only on simple linear interpolation of deep convolutional features from pre-trained convnets. We show that despite its simplicity, DFI can perform high-level semantic transformations like "make older/younger", "make bespectacled", "add smile", among others, surprisingly well - sometimes even matching or outperforming the state-of-the-art. This is particularly unexpected as DFI requires no specialized network architecture or even any deep network to be trained for these tasks. DFI therefore can be used as a new baseline to evaluate more complex algorithms and provides a practical answer to the question of which image transformation tasks are still challenging in the rise of deep learning.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computer Vision