TL;DR
This paper introduces a new high-quality dataset for facial-sketch synthesis, reviews existing methods, and proposes a simple yet effective baseline model that outperforms previous approaches, advancing FSS research.
Contribution
The paper provides the first comprehensive benchmark for FSS, introduces the FS2K dataset, and proposes the FSGAN model that significantly improves synthesis performance.
Findings
FS2K dataset enhances diversity and scalability for FSS research
FSGAN outperforms all previous models on FS2K dataset
Comprehensive review of 89 classical FSS methods
Abstract
This paper aims to conduct a comprehensive study on facial-sketch synthesis (FSS). However, due to the high costs of obtaining hand-drawn sketch datasets, there lacks a complete benchmark for assessing the development of FSS algorithms over the last decade. We first introduce a high-quality dataset for FSS, named FS2K, which consists of 2,104 image-sketch pairs spanning three types of sketch styles, image backgrounds, lighting conditions, skin colors, and facial attributes. FS2K differs from previous FSS datasets in difficulty, diversity, and scalability and should thus facilitate the progress of FSS research. Second, we present the largest-scale FSS investigation by reviewing 89 classical methods, including 25 handcrafted feature-based facial-sketch synthesis approaches, 29 general translation methods, and 35 image-to-sketch approaches. Besides, we elaborate comprehensive experiments…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
