SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.00833 · ECCV · 2022

PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation

Chao Chen, Qi Zhang, Rongrong Ji, Yiyi Zhou, Xiaoshuai Sun, Yunhang Shen, Jing He, Jun Peng

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 by a multistage paradigm, 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 to the latest pixel synthesis method called 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. Our source code is available at https://github.com/BlingHe/PixelFolder.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2204.00833")
get_code_for_paper("2204.00833")
have("2204.00833")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2204.00833.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2204.00833.svg)](https://syntology.ai/paper/2204.00833)

Connect an agent — have() is free.