Pixel synthesis is a promising research paradigm for image generation, which can well exploit pixel-wise prior knowledge for generation. However, existing methods still suffer from excessive memory footprint and computation overhead. In this paper, we propose a progressive pixel synthesis network towards efficient image generation, coined as PixelFolder. Specifically, PixelFolder formulates image generation as a progressive pixel regression problem and synthesizes images via a multi-stage structure, which can greatly reduce the overhead caused by large tensor transformations. In addition, we introduce novel pixel folding operations to further improve model efficiency while maintaining pixel-wise prior knowledge for end-to-end regression. With these innovative designs, we greatly reduce the expenditure of pixel synthesis, e.g., reducing 89% computation and 53% parameters compared with the latest pixel synthesis method CIPS. To validate our approach, we conduct extensive experiments on two benchmark datasets, namely FFHQ and LSUN Church. The experimental results show that with much less expenditure, PixelFolder obtains new state-of-the-art (SOTA) performance on two benchmark datasets, i.e., 3.77 FID and 2.45 FID on FFHQ and LSUN Church, respectively.Meanwhile, PixelFolder is also more efficient than the SOTA methods like StyleGAN2, reducing about 72% computation and 31% parameters, respectively. These results greatly validate the effectiveness of the proposed PixelFolder.
翻译:Pixel 合成是图像生成的一个很有希望的研究范例, 它可以很好地利用像素先前的知识来生成。 但是, 现有的方法仍然受到过量的记忆足迹和计算间接费用的影响。 在本文中, 我们提议建立一个进步的像素合成网络, 以高效生成图像, 被称作 PixelFolder 。 具体地说, PixelFolder 将图像生成作为一种渐进像素回归问题, 并通过多阶段结构合成图像, 这可以大大降低由大型沙拉变造成的管理管理管理。 此外, 我们引入了新型像素折叠操作, 以进一步提高模型效率, 同时保持像素之前的知识, 用于终端到终端的回归。 通过这些创新的设计, 我们大幅削减了像素合成成本的89%和53%参数, 与最新的像素合成方法 CIPPPPPPPS。 为了验证我们的方法, 我们在两个基准数据集上进行了广泛的实验, 即 FF 和 LSHUN Church 。 此外, 实验结果表明, Pix Folder 获得新的 State-feral 3, AS 和 Stal Q.