Adversarial Open Domain Adaption for Sketch-to-Photo Synthesis

12 Apr 2021  ·  Xiaoyu Xiang, Ding Liu, Xiao Yang, Yiheng Zhu, Xiaohui Shen, Jan P. Allebach ·

In this paper, we explore the open-domain sketch-to-photo translation, which aims to synthesize a realistic photo from a freehand sketch with its class label, even if the sketches of that class are missing in the training data. It is challenging due to the lack of training supervision and the large geometry distortion between the freehand sketch and photo domains... To synthesize the absent freehand sketches from photos, we propose a framework that jointly learns sketch-to-photo and photo-to-sketch generation. However, the generator trained from fake sketches might lead to unsatisfying results when dealing with sketches of missing classes, due to the domain gap between synthesized sketches and real ones. To alleviate this issue, we further propose a simple yet effective open-domain sampling and optimization strategy to "fool" the generator into treating fake sketches as real ones. Our method takes advantage of the learned sketch-to-photo and photo-to-sketch mapping of in-domain data and generalizes them to the open-domain classes. We validate our method on the Scribble and SketchyCOCO datasets. Compared with the recent competing methods, our approach shows impressive results in synthesizing realistic color, texture, and maintaining the geometric composition for various categories of open-domain sketches. read more

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Sketch-to-Image Translation Scribble AODB (full) FID 109.5 # 1
Accuracy 50% # 2
Human (%) 28.80 # 1
Sketch-to-Image Translation SketchyCOCO AODB (full) FID 58.8 # 1
Accuracy 38.3% # 2
Human (%) 29.00 # 1

Methods


No methods listed for this paper. Add relevant methods here