EvTexture：面向视频超分辨率的事件驱动纹理增强

EvTexture: Event-driven Texture Enhancement for Video Super-Resolution

June 19, 2024

作者: Dachun Kai, Jiayao Lu, Yueyi Zhang, Xiaoyan Sun

cs.AI

摘要

基于事件的视觉因其高时间分辨率和高动态范围等独特特性而受到越来越多的关注。最近，它被用于视频超分辨率（VSR）以增强流估计和时间对齐。本文提出了一种新的VSR方法，名为EvTexture，该方法不是用于运动学习，而是利用事件信号进行纹理增强。EvTexture利用事件的高频细节更好地恢复VSR中的纹理区域。在EvTexture中，引入了一个新的纹理增强分支。我们进一步引入了一个迭代纹理增强模块，逐步探索高时间分辨率事件信息以进行纹理恢复。这使得在多次迭代中逐渐改进纹理区域，从而获得更准确丰富的高分辨率细节。实验结果表明，我们的EvTexture在四个数据集上实现了最先进的性能。对于具有丰富纹理的Vid4数据集，我们的方法与最近的基于事件的方法相比，可以获得高达4.67dB的增益。源代码：https://github.com/DachunKai/EvTexture。

English

Event-based vision has drawn increasing attention due to its unique characteristics, such as high temporal resolution and high dynamic range. It has been used in video super-resolution (VSR) recently to enhance the flow estimation and temporal alignment. Rather than for motion learning, we propose in this paper the first VSR method that utilizes event signals for texture enhancement. Our method, called EvTexture, leverages high-frequency details of events to better recover texture regions in VSR. In our EvTexture, a new texture enhancement branch is presented. We further introduce an iterative texture enhancement module to progressively explore the high-temporal-resolution event information for texture restoration. This allows for gradual refinement of texture regions across multiple iterations, leading to more accurate and rich high-resolution details. Experimental results show that our EvTexture achieves state-of-the-art performance on four datasets. For the Vid4 dataset with rich textures, our method can get up to 4.67dB gain compared with recent event-based methods. Code: https://github.com/DachunKai/EvTexture.