文献类型：会议论文

英文题名：WaveGAN: Frequency-Aware GAN for High-Fidelity Few-Shot Image Generation

作者：Yang, Mengping[1,2];Wang, Zhe[1,2];Chi, Ziqiu[1,2];Feng, Wenyi[1,2]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai, Peoples R China;[2]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Shanghai, Peoples R China

会议论文集：17th European Conference on Computer Vision (ECCV)

会议日期：OCT 23-27, 2022

会议地点：Tel Aviv, ISRAEL

语种：英文

外文关键词：GANs; Few-shot learning; Image generation; Wavelet trasformation

摘要：Existing few-shot image generation approaches typically employ fusion-based strategies, either on the image or the feature level, to produce new images. However, previous approaches struggle to synthesize high-frequency signals with fine details, deteriorating the synthesis quality. To address this, we propose WaveGAN, a frequencyaware model for few-shot image generation. Concretely, we disentangle encoded features into multiple frequency components and perform low-frequency skip connections to preserve outline and structural information. Then we alleviate the generator's struggles of synthesizing fine details by employing high-frequency skip connections, thus providing informative frequency information to the generator. Moreover, we utilize a frequency L1-loss on the generated and real images to further impede frequency information loss. Extensive experiments demonstrate the effectiveness and advancement of our method on three datasets. Noticeably, we achieve new state-of-the-art with FID 42.17, LPIPS 0.3868, FID 30.35, LPIPS 0.5076, and FID 4.96, LPIPS 0.3822 respectively on Flower, Animal Faces, and VGGFace. GitHub: https://github.com/kobeshegu/ECCV2022 WaveGAN.