PixelGen: Improving Pixel Diffusion with Perceptual Supervision

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ma, Zehong, Xu, Ruihan, Zhang, Shiliang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909019011022848
author Ma, Zehong
Xu, Ruihan
Zhang, Shiliang
author_facet Ma, Zehong
Xu, Ruihan
Zhang, Shiliang
contents Pixel diffusion generates images directly in pixel space, avoiding the VAE artifacts and representational bottlenecks of two-stage latent diffusion. Recent JiT further simplifies pixel diffusion with x-prediction, where the model predicts clean images rather than velocity. However, the standard pixel-wise diffusion loss treats all pixels equally, spending model capacity to perceptually insignificant signals and often leading to blurry samples. We propose PixelGen, an end-to-end pixel diffusion framework that augments x-prediction with perceptual supervision. Specifically, PixelGen introduces two complementary perceptual losses on top of x-prediction: an LPIPS loss for local textures and a P-DINO loss for global semantics. To preserve sample coverage, PixelGen further proposes a noise-gating strategy that applies these losses only at lower-noise timesteps. On ImageNet-256 without classifier-free guidance, PixelGen achieves an FID of 5.11 in 80 training epochs, surpassing the latent diffusion baselines. Moreover, PixelGen scales efficiently to text-to-image generation, reaching a GenEval score of 0.79 with only 6 days of training on 8xH800 GPUs. These results show that perceptual supervision substantially narrows the gap between pixel and latent diffusion while preserving a simple one-stage pipeline. Codes are available at https://github.com/Zehong-Ma/PixelGen.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02493
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PixelGen: Improving Pixel Diffusion with Perceptual Supervision
Ma, Zehong
Xu, Ruihan
Zhang, Shiliang
Computer Vision and Pattern Recognition
Artificial Intelligence
Pixel diffusion generates images directly in pixel space, avoiding the VAE artifacts and representational bottlenecks of two-stage latent diffusion. Recent JiT further simplifies pixel diffusion with x-prediction, where the model predicts clean images rather than velocity. However, the standard pixel-wise diffusion loss treats all pixels equally, spending model capacity to perceptually insignificant signals and often leading to blurry samples. We propose PixelGen, an end-to-end pixel diffusion framework that augments x-prediction with perceptual supervision. Specifically, PixelGen introduces two complementary perceptual losses on top of x-prediction: an LPIPS loss for local textures and a P-DINO loss for global semantics. To preserve sample coverage, PixelGen further proposes a noise-gating strategy that applies these losses only at lower-noise timesteps. On ImageNet-256 without classifier-free guidance, PixelGen achieves an FID of 5.11 in 80 training epochs, surpassing the latent diffusion baselines. Moreover, PixelGen scales efficiently to text-to-image generation, reaching a GenEval score of 0.79 with only 6 days of training on 8xH800 GPUs. These results show that perceptual supervision substantially narrows the gap between pixel and latent diffusion while preserving a simple one-stage pipeline. Codes are available at https://github.com/Zehong-Ma/PixelGen.
title PixelGen: Improving Pixel Diffusion with Perceptual Supervision
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2602.02493