论文标题
事件增强了高质量的图像恢复
Event Enhanced High-Quality Image Recovery
论文作者
论文摘要
具有极高的时间分辨率，事件摄像机具有机器人技术和计算机视觉的巨大潜力。但是，它们的异步成像机制通常会加剧对噪音的测量敏感性，并带来身体负担，以增加图像空间分辨率。为了恢复高质量的强度图像，应该解决事件摄像机的Denoisis和超分辨率问题。由于事件描绘了亮度的变化，随着事件的增强变性模型，可以从嘈杂，模糊和低分辨率强度观察结果中恢复清晰而尖锐的高分辨率潜在图像。可以共同考虑利用稀疏学习，事件和低分辨率强度观察的框架。基于此，我们提出了一个可解释的网络，即事件增强的稀疏学习网络（ESL-NET），以从事件摄像机中恢复高质量的图像。在使用合成数据集进行了训练之后，提出的ESL-NET可以在很大程度上提高最先进的ART性能7-12 dB。此外，如果没有其他训练过程，就可以轻松扩展所提出的ESL-NET，以产生与事件一样高的帧速率的连续帧。
With extremely high temporal resolution, event cameras have a large potential for robotics and computer vision. However, their asynchronous imaging mechanism often aggravates the measurement sensitivity to noises and brings a physical burden to increase the image spatial resolution. To recover high-quality intensity images, one should address both denoising and super-resolution problems for event cameras. Since events depict brightness changes, with the enhanced degeneration model by the events, the clear and sharp high-resolution latent images can be recovered from the noisy, blurry and low-resolution intensity observations. Exploiting the framework of sparse learning, the events and the low-resolution intensity observations can be jointly considered. Based on this, we propose an explainable network, an event-enhanced sparse learning network (eSL-Net), to recover the high-quality images from event cameras. After training with a synthetic dataset, the proposed eSL-Net can largely improve the performance of the state-of-the-art by 7-12 dB. Furthermore, without additional training process, the proposed eSL-Net can be easily extended to generate continuous frames with frame-rate as high as the events.
