生成式细化网络 GRN：面向视觉合成的新一代范式

View PDF HTML (experimental)

Abstract:While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless of different complexity. In contrast, autoregressive (AR) models are inherently complexity-aware, as evidenced by their variable likelihoods, but are often hindered by lossy discrete tokenization and error accumulation. In this work, we introduce Generative Refinement Networks (GRN), a next-generation visual synthesis paradigm that addresses these issues. At its core, GRN addresses the discrete tokenization bottleneck through a theoretically near-lossless Hierarchical Binary Quantization (HBQ), achieving a reconstruction quality comparable to continuous counterparts. Built upon HBQ's latent space, GRN fundamentally upgrades AR generation with a global refinement mechanism that progressively perfects and corrects artworks -- like a human artist painting. Besides, GRN integrates an entropy-guided sampling strategy, enabling complexity-aware, adaptive-step generation without compromising visual quality. On the ImageNet benchmark, GRN establishes new records in image reconstruction (0.56 rFID) and class-conditional image generation (1.81 gFID). We also scale GRN to more challenging text-to-image and text-to-video generation, delivering superior performance on an equivalent scale. We release all models and code to foster further research on GRN.

Comments:	code: this https URL
Subjects:	Computer Vision and Pattern Recognition (cs.CV)
Cite as:	arXiv:2604.13030 [cs.CV]
	(or arXiv:2604.13030v2 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2604.13030 arXiv-issued DOI via DataCite

Submission history

From: Jian Han [view email]
[v1] Tue, 14 Apr 2026 17:59:03 UTC (12,163 KB)
[v2] Tue, 7 Jul 2026 13:17:16 UTC (12,129 KB)