视觉合成的生成式精化网络

摘要

尽管扩散模型在视觉生成领域占据主导地位，但其计算效率低下，无论复杂度差异均采用统一计算负荷。相比之下，自回归模型通过其可变的似然度展现出天然的复杂度感知能力，但常因有损的离散化标记和误差累积而受限。本研究提出生成式精修网络（GRN），一种新一代视觉合成范式以解决上述问题。GRN的核心突破在于通过理论近乎无损的层次化二值量化（HBQ）攻克离散标记化瓶颈，其重建质量可与连续表征相媲美。基于HBQ的潜空间，GRN通过全局精修机制对自回归生成进行根本性升级——该机制如同人类艺术家作画般逐步完善和修正作品。此外，GRN融合了熵引导采样策略，在保持视觉质量的前提下实现复杂度感知的自适应步长生成。在ImageNet基准测试中，GRN创下图像重建（0.56 rFID）和类别条件图像生成（1.81 gFID）的新纪录。我们还将GRN扩展至更具挑战性的文本到图像及文本到视频生成任务，在同等规模下实现卓越性能。现公开全部模型与代码，以推动GRN的后续研究。

English

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 to address 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.

视觉合成的生成式精化网络

Generative Refinement Networks for Visual Synthesis

摘要

Support