arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.06174cs.CVcs.AI
收藏

实现快速准确的真实世界深度超分辨率:基准数据集和基线

Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline

Institute of Information Science, Beijing Jiaotong University(北京交通大学信息科学研究所);Beijing Key Laboratory of Advanced Information Science and Network(北京先进信息科学与网络重点实验室)

Lingzhi He, Hongguang Zhu, Feng Li, Huihui Bai, Runmin Cong, Chunjie Zhang, Chunyu Lin, Meiqin Liu, Yao Zhao

摘要:

商业深度传感器获得的深度图通常是低分辨率的,这使得其难以用于各种计算机视觉任务。因此,深度图超分辨率(SR)是一个实用且有价值的任务,其将深度图放大到高分辨率(HR)空间中。然而,受限于缺乏真实世界成对的低分辨率(LR)和HR深度图,大多数现有方法使用下采样来获得成对的训练样本。为此,我们首先构建了一个名为“RGB-D-D”的大规模数据集,它可以极大地促进深度图SR甚至更多深度相关现实任务的研究。我们数据集中的“D-D”表示分别从手机和Lucid Helios捕获的成对LR和HR深度图,范围从室内场景到具有挑战性的室外场景。此外,我们提供了一个快速的深度图超分辨率(FDSR)的基线,其中的高频分量自适应分解从RGB图像,以指导深度图SR。广泛的实验上现有的公共数据集证明了我们的网络的有效性和效率相比,国家的最先进的方法。此外,对于真实世界的LR深度图,我们的算法可以产生更准确的HR深度图,具有更清晰的边界,并在一定程度上纠正深度值的错误。

英文摘要:

Depth maps obtained by commercial depth sensors are always in low-resolution, making it difficult to be used in various computer vision tasks. Thus, depth map super-resolution (SR) is a practical and valuable task, which upscales the depth map into high-resolution (HR) space. However, limited by the lack of real-world paired low-resolution (LR) and HR depth maps, most existing methods use downsampling to obtain paired training samples. To this end, we first construct a large-scale dataset named "RGB-D-D", which can greatly promote the study of depth map SR and even more depth-related real-world tasks. The "D-D" in our dataset represents the paired LR and HR depth maps captured from mobile phone and Lucid Helios respectively ranging from indoor scenes to challenging outdoor scenes. Besides, we provide a fast depth map super-resolution (FDSR) baseline, in which the high-frequency component adaptively decomposed from RGB image to guide the depth map SR. Extensive experiments on existing public datasets demonstrate the effectiveness and efficiency of our network compared with the state-of-the-art methods. Moreover, for the real-world LR depth maps, our algorithm can produce more accurate HR depth maps with clearer boundaries and to some extent correct the depth value errors.

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。

↑