Editing in Style: Uncovering the Local Semantics of GANs
| Autor: | Raja Bala, Sabine Süsstrunk, Bob Price, Edo Collins |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning business.industry Computer science media_common.quotation_subject Computer Vision and Pattern Recognition (cs.CV) Locality Interpolation (computer graphics) Computer Science - Computer Vision and Pattern Recognition 010501 environmental sciences Semantics 01 natural sciences Image (mathematics) Machine Learning (cs.LG) 010104 statistics & probability Morphing Human–computer interaction Quality (business) Artificial intelligence 0101 mathematics business Control (linguistics) 0105 earth and related environmental sciences media_common |
| Zdroj: | CVPR |
| DOI: | 10.48550/arxiv.2004.14367 |
| Popis: | While the quality of GAN image synthesis has improved tremendously in recent years, our ability to control and condition the output is still limited. Focusing on StyleGAN, we introduce a simple and effective method for making local, semantically-aware edits to a target output image. This is accomplished by borrowing elements from a source image, also a GAN output, via a novel manipulation of style vectors. Our method requires neither supervision from an external model, nor involves complex spatial morphing operations. Instead, it relies on the emergent disentanglement of semantic objects that is learned by StyleGAN during its training. Semantic editing is demonstrated on GANs producing human faces, indoor scenes, cats, and cars. We measure the locality and photorealism of the edits produced by our method, and find that it accomplishes both. Comment: IEEE Conference on Computer Vision and Patten Recognition (CVPR), 2020. Code: https://github.com/IVRL/GANLocalEditing |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|