Deep Lidar-guided 图像去模糊
Deep Lidar-guided Image Deblurring
AI总结：
本研究针对低光照等场景下的图像运动模糊问题，提出结合移动Lidar深度信息的通用适配器结构与持续学习策略，将现有神经去模糊模型转为深度感知模型，在真实手机Lidar数据集上验证了深度信息可显著提升去模糊效果。
摘要：
便携式激光雷达（Lidar）设备的兴起，包括其在智能手机中的应用，为新型计算成像技术打开了大门。作为一种主动传感设备，Lidar 能够为被动光学传感器提供补充数据，尤其是在低光照成像这类运动模糊会影响照片的场景中。本文研究了移动 Lidar 传感器提供的深度信息是否对图像去模糊任务有用，以及如何将其与一种通用方法相结合，该方法可将任意最先进的神经去模糊模型转换为深度感知模型。为此，我们开发了一种通用适配器结构，可高效预处理深度信息，用深度特征调制图像特征。此外，我们对预训练的编码器-解码器模型应用了持续学习策略，使其能够以最少的额外数据需求，将深度信息作为额外输入纳入模型。我们在由智能手机 Lidar 采集的真实深度数据构成的数据集上验证表明，利用真实深度信息可以显著提升去模糊算法的效果。
英文摘要：
The rise of portable Lidar instruments, including their adoption in smartphones, opens the door to novel computational imaging techniques. Being an active sensing instrument, Lidar can provide complementary data to passive optical sensors, particularly in situations like low-light imaging where motion blur can affect photos. In this paper, we study if the depth information provided by mobile Lidar sensors is useful for the task of image deblurring and how to integrate it with a general approach that transforms any state-of-the-art neural deblurring model into a depth-aware one. To achieve this, we developed a universal adapter structure that efficiently preprocesses the depth information to modulate image features with depth features. Additionally, we applied a continual learning strategy to pretrained encoder-decoder models, enabling them to incorporate depth information as an additional input with minimal extra data requirements. We demonstrate that utilizing true depth information can significantly boost the effectiveness of deblurring algorithms, as validated on a dataset with real-world depth data captured by a smartphone Lidar.
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。
