Zhang Shansi, Meng Nan, Lam Edmund Y
IEEE Trans Image Process. 2023;32:4314-4326. doi: 10.1109/TIP.2023.3297412. Epub 2023 Aug 1.
Light field (LF) images containing information for multiple views have numerous applications, which can be severely affected by low-light imaging. Recent learning-based methods for low-light enhancement have some disadvantages, such as a lack of noise suppression, complex training process and poor performance in extremely low-light conditions. To tackle these deficiencies while fully utilizing the multi-view information, we propose an efficient Low-light Restoration Transformer (LRT) for LF images, with multiple heads to perform intermediate tasks within a single network, including denoising, luminance adjustment, refinement and detail enhancement, achieving progressive restoration from small scale to full scale. Moreover, we design an angular transformer block with an efficient view-token scheme to model the global angular dependencies, and a multi-scale spatial transformer block to encode the multi-scale local and global information within each view. To address the issue of insufficient training data, we formulate a synthesis pipeline by simulating the major noise sources with the estimated noise parameters of LF camera. Experimental results demonstrate that our method achieves the state-of-the-art performance on low-light LF restoration with high efficiency.
包含多视图信息的光场（LF）图像有众多应用，但可能会受到低光成像的严重影响。最近基于学习的低光增强方法存在一些缺点，如缺乏噪声抑制、训练过程复杂以及在极低光条件下性能不佳。为了在充分利用多视图信息的同时解决这些不足，我们提出了一种用于LF图像的高效低光恢复Transformer（LRT），它具有多个头，可在单个网络内执行中间任务，包括去噪、亮度调整、细化和细节增强，实现从小尺度到全尺度的渐进式恢复。此外，我们设计了一个具有高效视图令牌方案的角度Transformer块来建模全局角度依赖性，以及一个多尺度空间Transformer块来编码每个视图内的多尺度局部和全局信息。为了解决训练数据不足的问题，我们通过用LF相机的估计噪声参数模拟主要噪声源来制定一个合成管道。实验结果表明，我们的方法在低光LF恢复方面高效地实现了当前最优性能。
