快速、忠实且逼真基于扩散的图像超分辨率与增强的流图模型
Fast, faithful and photorealistic diffusion-based image super-resolution with enhanced Flow Map models
AI总结:
本文提出FlowMapSR,一种基于扩散的图像超分辨率框架,通过增强流图模型和对抗微调提升效率和逼真度,实现高 fidelity 和快速推理。
摘要:
基于扩散的图像超分辨率(SR)最近通过利用大规模预训练的文本到图像扩散模型(DMs)的表达能力而引起了广泛关注。一个核心的实践挑战是解决重建忠实度和逼真度之间的权衡。为了解决推理效率问题,许多近期工作探索了专门针对SR的知识蒸馏策略,使能够一步扩散方法。然而,这些教师-学生方案本质上受信息压缩的限制,即使整体感知质量高,也可能降低诸如逼真纹理和景深等感知线索。同时,自蒸馏DMs,即流图模型,已作为图像生成任务的有前途的替代方案出现,使能够快速推理同时保持标准DMs的表达性和训练稳定性。基于这些发展,我们提出了FlowMapSR,一种新的基于扩散的框架,专门设计用于高效的推理。除了将流图模型适应于SR之外,我们还引入了两种互补的增强:(i)基于分类器自由引导范式泛化的正负提示引导,以及(ii)使用低秩适应(LoRA)的对抗微调。在考虑的流图公式(欧拉、拉格朗日和快捷)中,我们发现快捷变体在结合这些增强时始终表现最佳。广泛的实验表明,FlowMapSR在x4和x8放大时比最近最先进的方法在重建忠实度和逼真度之间取得了更好的平衡,同时保持了竞争性的推理时间。值得注意的是,一个模型用于两种放大因子,没有任何特定尺度的条件或退化引导机制。
英文摘要:
Diffusion-based image super-resolution (SR) has recently attracted significant attention by leveraging the expressive power of large pre-trained text-to-image diffusion models (DMs). A central practical challenge is resolving the trade-off between reconstruction faithfulness and photorealism. To address inference efficiency, many recent works have explored knowledge distillation strategies specifically tailored to SR, enabling one-step diffusion-based approaches. However, these teacher-student formulations are inherently constrained by information compression, which can degrade perceptual cues such as lifelike textures and depth of field, even with high overall perceptual quality. In parallel, self-distillation DMs, known as Flow Map models, have emerged as a promising alternative for image generation tasks, enabling fast inference while preserving the expressivity and training stability of standard DMs. Building on these developments, we propose FlowMapSR, a novel diffusion-based framework for image super-resolution explicitly designed for efficient inference. Beyond adapting Flow Map models to SR, we introduce two complementary enhancements: (i) positive-negative prompting guidance, based on a generalization of classifier free-guidance paradigm to Flow Map models, and (ii) adversarial fine-tuning using Low-Rank Adaptation (LoRA). Among the considered Flow Map formulations (Eulerian, Lagrangian, and Shortcut), we find that the Shortcut variant consistently achieves the best performance when combined with these enhancements. Extensive experiments show that FlowMapSR achieves a better balance between reconstruction faithfulness and photorealism than recent state-of-the-art methods for both x4 and x8 upscaling, while maintaining competitive inference time. Notably, a single model is used for both upscaling factors, without any scale-specific conditioning or degradation-guided mechanisms.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。