WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generation
This addresses the challenge of generating high-fidelity images with fine details in few-shot learning, which is incremental as it builds on existing fusion-based methods.
The paper tackles the problem of synthesizing high-frequency details in few-shot image generation by proposing WaveGAN, a frequency-aware model that disentangles features into frequency components and uses skip connections and a frequency loss, achieving state-of-the-art FID and LPIPS scores on three datasets.
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 frequency-aware 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