用状态空间模型实现轻量级光场图像超分，速度更快效果更好
$L^2$FMamba: Lightweight Light Field Image Super-Resolution with State Space Model
- 基于渐进特征提取设计新模块，高效捕捉光场图像长程依赖
- 参数量更低、推理速度更快，多个数据集上性能超越现有方法
- 适合需要快速高精度超分的光场成像应用
Transformer 因其建模长程依赖的能力，在光场图像超分辨率任务中表现显著提升。然而，其核心自注意力机制固有的高计算复杂度日益制约该任务的发展。为此，我们提出 LF-VSSM 模块，受渐进特征提取启发，可高效捕获光场图像中的关键长程空间-视角依赖关系：依次提取子孔径图像内的空间特征、子孔径图像间的空间-视角特征，以及光场像素间的空间-视角特征。在此基础上，我们构建轻量级网络 $L^2$FMamba（Lightweight Light Field Mamba），融合 LF-VSSM 模块，利用光场特性实现超分，同时克服 Transformer 方法的计算瓶颈。在多个光场数据集上的大量实验表明，本方法在减少参数量与计算复杂度的同时，实现了更优的超分辨率性能，并具备更快的推理速度。
原文摘要 · Abstract (English)
Transformers bring significantly improved performance to the light field image super-resolution task due to their long-range dependency modeling capability. However, the inherently high computational complexity of their core self-attention mechanism has increasingly hindered their advancement in this task. To address this issue, we first introduce the LF-VSSM block, a novel module inspired by progressive feature extraction, to efficiently capture critical long-range spatial-angular dependencies in light field images. LF-VSSM successively extracts spatial features within sub-aperture images, spatial-angular features between sub-aperture images, and spatial-angular features between light field image pixels. On this basis, we propose a lightweight network, $L^2$FMamba (Lightweight Light Field Mamba), which integrates the LF-VSSM block to leverage light field features for super-resolution tasks while overcoming the computational challenges of Transformer-based approaches. Extensive experiments on multiple light field datasets demonstrate that our method reduces the number of parameters and complexity while achieving superior super-resolution performance with faster inference speed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。