arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.01732cs.CV
收藏

用于单目深度估计的高分辨率合成RGB-D数据集

High-Resolution Synthetic RGB-D Datasets for Monocular Depth Estimation

K|Lens GmbH(K|Lens有限公司);Saarland Informatics Campus(萨尔信息学园区);MPI Informatics(马克斯·普朗克信息学研究所);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心(DFKI))

Aakash Rajpal, Noshaba Cheema, Klaus Illgner-Fehns, Philipp Slusallek, Sunil Jaiswal

AI总结:

针对现有单目深度估计数据集分辨率低、泛化差的问题,研究从GTA-V生成高分辨率合成HRSD数据集,改进DPT算法结构与损失,显著提升深度估计准确率。

摘要:

精确的深度图在自动驾驶、场景重建、点云生成等各类应用中至关重要。然而,单目深度估计(MDE)算法往往无法提供足够的纹理与清晰度,在均质场景中也存在结果不一致的问题。这类算法大多采用基于CNN或视觉Transformer的架构,需要大规模数据集用于监督训练。但在现有深度数据集上训练的MDE算法泛化能力不佳,因此无法在多样的真实场景中实现准确的性能表现。此外,现有深度真值图要么分辨率较低,要么呈稀疏状态,导致生成的深度图相对不一致。总体而言,获取具备像素级精度的高分辨率真值数据集以实现准确深度预测,是一项成本高昂且耗时的挑战。\n本文中,我们从《Grand Theft Auto V》(GTA-V,侠盗猎车手5)中生成了一个尺寸为1920×1080的高分辨率合成深度数据集(HRSD),包含100000张彩色图像及对应的稠密真值深度图。生成的数据集具备多样性,涵盖从室内到室外、从均质表面到纹理丰富的各类场景。为开展实验与分析,我们在提出的合成数据集上训练了DPT算法——一种当前最优的基于Transformer的MDE算法,该算法在不同场景下的深度图准确率显著提升了9%。由于合成数据集分辨率更高,我们提出在Transformer编码器中加入特征提取模块,并引入基于注意力的损失函数,使准确率进一步提升了15%。

英文摘要:

Accurate depth maps are essential in various applications, such as autonomous driving, scene reconstruction, point-cloud creation, etc. However, monocular-depth estimation (MDE) algorithms often fail to provide enough texture & sharpness, and also are inconsistent for homogeneous scenes. These algorithms mostly use CNN or vision transformer-based architectures requiring large datasets for supervised training. But, MDE algorithms trained on available depth datasets do not generalize well and hence fail to perform accurately in diverse real-world scenes. Moreover, the ground-truth depth maps are either lower resolution or sparse leading to relatively inconsistent depth maps. In general, acquiring a high-resolution ground truth dataset with pixel-level precision for accurate depth prediction is an expensive, and time-consuming challenge. In this paper, we generate a high-resolution synthetic depth dataset (HRSD) of dimension 1920 X 1080 from Grand Theft Auto (GTA-V), which contains 100,000 color images and corresponding dense ground truth depth maps. The generated datasets are diverse and have scenes from indoors to outdoors, from homogeneous surfaces to textures. For experiments and analysis, we train the DPT algorithm, a state-of-the-art transformer-based MDE algorithm on the proposed synthetic dataset, which significantly increases the accuracy of depth maps on different scenes by 9 %. Since the synthetic datasets are of higher resolution, we propose adding a feature extraction module in the transformer encoder and incorporating an attention-based loss, further improving the accuracy by 15 %.

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。

↑