发表机构
University of California, Berkeley（加州大学伯克利分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RTLViT是一种轻量级纯数据驱动的视觉Transformer，仅用109万参数实现高质量实时无透镜重建，比15倍参数架构PSNR提升3.46 dB，并已在手机和笔记本上验证实时性能。
AI 中文摘要
基于掩模的无透镜成像器利用简单紧凑的硬件捕获测量值，并通过重建算法恢复图像。重建算法影响成像系统的图像质量、推理速度和计算需求，通常需要在图像质量与计算效率之间进行权衡。向集成式无透镜成像器（即在单一设备（如手机）内完成编码和重建）推进，需要一种快速、高质量且实用的重建方法。我们提出了实时无透镜视觉Transformer（RTLViT），这是一种轻量级、纯数据驱动的重建架构，用于高质量和实时的无透镜重建。RTLViT仅需109万个可学习参数，便能提供比实时基线方法和规模大得多的基于注意力的架构更高质量的重建结果，包括在峰值信噪比上比具有15倍可学习参数的架构提升高达3.46 dB。我们证明了RTLViT在广泛的训练数据集规模和两种不同掩模设计（微透镜阵列和扩散器）下均能保持高质量的重建。最后，我们在笔记本电脑和智能手机上实现了基于RTLViT的实时重建，为未来用于实时应用的集成式无透镜成像器提供支持。
英文摘要
Mask-based lensless imagers capture measurements using simple, compact hardware and recover images using a reconstruction algorithm. The reconstruction algorithm affects the image quality, inference speed, and computational requirements of the imaging system, often trading off image quality against computational efficiency. Advancing toward integrated lensless imagers, where encoding and reconstruction occur within a single device (e.g., a mobile phone), requires a fast, high-quality, and practical reconstruction method. We introduce the Real-Time Lensless Vision Transformer (RTLViT), a lightweight, purely data-driven reconstruction architecture for high-quality and real-time lensless reconstruction. With only 1.09 million learnable parameters, RTLViT provides higher-quality reconstructions than both real-time baselines and substantially larger attention-based architectures, including improvements of up to 3.46 dB in peak signal-to-noise ratio over architectures with $15 \times$ more learnable parameters. We demonstrate that RTLViT maintains high-quality reconstructions across a wide range of training dataset sizes and two different mask designs (lenslets and a diffuser). Finally, we implement real-time reconstruction with RTLViT on laptops and smartphones, supporting future integrated lensless imagers for real-time applications.
Comments9 pages, 6 figures
