arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.15490cs.CVcs.AI
收藏

RPT-SR:区域先验注意力变换器用于红外图像超分辨率

RPT-SR: Regional Prior attention Transformer for infrared image Super-Resolution

Yonsei University(延世大学)

Youngwan Jin, Incheol Park, Yagiz Nalcakan, Hyeongjin Ju, Sanghyeop Yeo, Shiho Kim

AI总结:

RPT-SR通过区域先验注意力机制提升红外图像超分辨率,结合可学习区域先验token与局部token,实现动态调节局部重建,展现广泛适用性与高性能。

摘要:

通用超分辨率模型,特别是视觉变换器,在通用场景中取得了显著成功,但在常见的红外成像场景如监控和自动驾驶中表现出根本性的效率低下,这些场景通常从固定或近静止的视角操作。这些模型未能利用此类场景中固有的强且持久的空间先验,导致冗余学习和次优性能。为此,我们提出了用于红外图像超分辨率的区域先验注意力变换器(RPT-SR),一种新的架构,将场景布局信息显式编码到注意力机制中。我们的核心贡献是一种双token框架,将(1)可学习的区域先验token,作为场景全局结构的持久记忆,与(2)局部token,捕捉当前输入的帧特定内容进行融合。通过将这些token输入注意力机制,我们的模型使先验能够动态调节局部重建过程。广泛的实验验证了我们的方法。虽然大多数先前工作专注于单一红外波段,我们通过在覆盖长波(LWIR)和短波(SWIR)谱的多样数据集上建立新的最先进性能,展示了RPT-SR的广泛适用性和灵活性。

英文摘要:

General-purpose super-resolution models, particularly Vision Transformers, have achieved remarkable success but exhibit fundamental inefficiencies in common infrared imaging scenarios like surveillance and autonomous driving, which operate from fixed or nearly-static viewpoints. These models fail to exploit the strong, persistent spatial priors inherent in such scenes, leading to redundant learning and suboptimal performance. To address this, we propose the Regional Prior attention Transformer for infrared image Super-Resolution (RPT-SR), a novel architecture that explicitly encodes scene layout information into the attention mechanism. Our core contribution is a dual-token framework that fuses (1) learnable, regional prior tokens, which act as a persistent memory for the scene's global structure, with (2) local tokens that capture the frame-specific content of the current input. By utilizing these tokens into an attention, our model allows the priors to dynamically modulate the local reconstruction process. Extensive experiments validate our approach. While most prior works focus on a single infrared band, we demonstrate the broad applicability and versatility of RPT-SR by establishing new state-of-the-art performance across diverse datasets covering both Long-Wave (LWIR) and Short-Wave (SWIR) spectra

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。

↑