- Title: EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
- Task: Image Inpainting
- Author: K. Nazeri, E. Ng, T. Joseph, F. Qureshi, and M. Ebrahimi
- Date: Jan. 2019
- Arxiv: 1901.00212
- Published: ICCV 2019 Workshop
Highlights & Drawbacks
- Interactive sketch editing for image completion
- A two-stage adversarial model that comprises of an edge generator followed by an image completion network.
Motivation & Design
The spirit: “lines first, color next”, which is partly in- spired by our understanding of how artists work.
Performance & Ablation Study
Left to Right: Original image, input image, generated edges, inpainted results without any post-processing.
Quantitative results over Places2 with models
Left to right: Contextual Attention (CA), Globally and Locally Consistent Image Completion (GLCIC), Partial Convolu- tion (PConv) , G1 and G2 (Ours), G2 only with Canny edges (Canny). The best result of each row is boldfaced except for Canny.