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
翻译:现有的微小图像生成方法通常采用基于图像或特征水平的聚合战略来生成新的图像。然而,以往的方法是努力以细细的细节合成高频信号,从而降低合成质量。为了解决这个问题,我们提议WaveGAN,这是一个用于少发图像生成的频率感知模型;具体地说,我们将编码的特性分解成多个频率组件,并进行低频跳动连接,以保存大纲和结构信息。然后我们利用高频跳出连接,从而向生成者提供信息频率信息,减轻生成者合成细细节的难度。此外,我们利用生成的和真实图像的频率L1损失,以进一步阻止频率信息丢失。广泛的实验表明我们在三个数据集上的方法的有效性和进步。值得注意的是,我们实现了与FID 42.17、LPIPPPS 0.3868、FID 30.35、LPIPS 0.5076和FID 4.96、LPPS 0.3822分别关于花瓶、动物面和VGGFAFA的0.382和LGFS/AN22_GUBS.G.GUV:http://WAGUBS/WA/WAGUBSUV。