Recent years have witnessed the proliferation of online fashion blogs and communities, where a large amount of fashion model images with chic clothes in various scenarios are publicly available. To facilitate users to find the corresponding clothes, we focus on studying how to generate pure wellshaped clothing items with the best view from the complex model images. Towards this end, inspired by painting, where the initial sketches and following coloring are both essential, we propose a two-stage shape-constrained clothing generative framework, dubbed as PaintNet. PaintNet comprises two coherent components: shape predictor and texture renderer. The shape predictor is devised to predict the intermediate shape map for the to-be-generated clothing item based on the latent representation learning, while the texture renderer is introduced to generate the final clothing image with the guidance of the predicted shape map. Extensive qualitative and quantitative experiments conducted on the public Lookbook dataset verify the effectiveness of PaintNet in clothing generation from fashion model images. Moreover, we also explore the potential of PaintNet in the task of cross-domain clothing retrieval, and the experiment results show that PaintNet can achieve, on average, 5.34% performance improvement over the traditional non-generative retrieval methods.

近年来，在线时尚博客和社区激增，其中大量公开了在各种情况下带有时髦衣服的时装模特图像。为了方便用户找到相应的衣服，我们专注于研究如何从复杂的模型图像中生成具有最佳视图的纯正形状的衣服。为此，受绘画的启发，最初的草图和随后的着色都是必不可少的，我们提出了一个两阶段形状受限制的服装生成框架，称为PaintNet。PaintNet包含两个相关的组件：形状预测器和纹理渲染器。形状预测器设计用于根据潜在表示学习预测待生成服装的中间形状图，同时引入纹理渲染器以在预测的形状图的指导下生成最终的服装图像。在公共Lookbook数据集上进行的大量定性和定量实验验证了PaintNet从时装模特图像生成服装的有效性。此外，我们还探索了PaintNet在跨域服装检索任务中的潜力，实验结果表明，与传统的非生成式检索方法相比，PaintNet的性能平均提高了5.34％。