arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.14840cs.CV
收藏

精确的几何数据对于密集3D视觉任务的重要性

On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks

Technical University of Munich(慕尼黑工业大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);Siemens AG(西门子股份公司)
HyunJun Jung, Patrick Ruhkamp, Guangyao Zhai, Nikolas Brasch, Yitong Li, Yannick Verdie, Jifei Song, Yiren Zhou, Anil Armagan, Slobodan Ilic, Ales Leonardis, Na… 展开作者

HyunJun Jung, Patrick Ruhkamp, Guangyao Zhai, Nikolas Brasch, Yitong Li, Yannick Verdie, Jifei Song, Yiren Zhou, Anil Armagan, Slobodan Ilic, Ales Leonardis, Nassir Navab, Benjamin Busam

摘要:

解决密集3D视觉问题的基于学习的方法通常在3D传感器数据上进行训练。分别使用的测量距离的原理提供了优点和缺点。由于缺乏多模态数据集,这些通常不会在文献中进行比较或讨论。无纹理区域对于来自运动运动恢复结构和立体声的结构是有问题的,反射材料对主动感测造成问题,并且半透明对象的距离对于用现有硬件测量是复杂的。对不准确或损坏的数据进行训练会导致模型偏差,并妨碍泛化能力。如果在评估过程中将传感器测量值视为地面实况,则这些影响仍然不会被注意到。本文研究了传感器误差对密集三维视觉任务深度估计和重建的影响。我们严格显示传感器特性对学习预测的重大影响,并注意到日常家庭环境中各种技术所产生的泛化问题。为了进行评估,我们引入了精心设计的数据集\footnote{dataset available at https://github.com/Junggy/HAMMER-dataset},其中包括来自商用传感器的测量结果,即D-ToF、I-ToF、无源/有源立体声和单目RGB+ P。我们的研究量化了相当大的传感器噪声影响,并为改善密集视觉估计和有针对性的数据融合铺平了道路。

英文摘要:

Learning-based methods to solve dense 3D vision problems typically train on 3D sensor data. The respectively used principle of measuring distances provides advantages and drawbacks. These are typically not compared nor discussed in the literature due to a lack of multi-modal datasets. Texture-less regions are problematic for structure from motion and stereo, reflective material poses issues for active sensing, and distances for translucent objects are intricate to measure with existing hardware. Training on inaccurate or corrupt data induces model bias and hampers generalisation capabilities. These effects remain unnoticed if the sensor measurement is considered as ground truth during the evaluation. This paper investigates the effect of sensor errors for the dense 3D vision tasks of depth estimation and reconstruction. We rigorously show the significant impact of sensor characteristics on the learned predictions and notice generalisation issues arising from various technologies in everyday household environments. For evaluation, we introduce a carefully designed dataset\footnote{dataset available at https://github.com/Junggy/HAMMER-dataset} comprising measurements from commodity sensors, namely D-ToF, I-ToF, passive/active stereo, and monocular RGB+P. Our study quantifies the considerable sensor noise impact and paves the way to improved dense vision estimates and targeted data fusion.

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。

↑