arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2207.11368cs.CV
收藏

Neural-Sim:使用NeRF学习生成训练数据

Neural-Sim: Learning to Generate Training Data with NeRF

University of Southern California(南加州大学);Microsoft Research(微软研究院)

Yunhao Ge, Harkirat Behl, Jiashu Xu, Suriya Gunasekar, Neel Joshi, Yale Song, Xin Wang, Laurent Itti, Vibhav Vineet

摘要:

训练计算机视觉模型通常需要在不同的场景配置和属性下收集和标记大量图像。这个过程非常耗时,而且很难确保捕获的数据分布很好地映射到应用程序场景的目标域。最近,合成数据已经成为解决这两个问题的一种方法。然而,现有的方法要么需要人类专家手动调整每个场景属性,要么使用几乎不提供控制的自动方法;这需要渲染大量的随机数据变化,这是缓慢的,并且通常对于目标域是次优的。我们提出了第一个完全可微的合成数据管道,该管道在具有目标应用程序的损失函数的闭环中使用神经辐射场(NeRFs)。我们的方法按需生成数据,无需人工劳动,以最大限度地提高目标任务的准确性。我们说明了我们的方法在合成和现实世界的目标检测任务的有效性。我们还介绍了一个新的“YCB在野外”的数据集和基准,提供了一个测试方案,目标检测与不同的姿态在现实世界的环境中。

英文摘要:

Training computer vision models usually requires collecting and labeling vast amounts of imagery under a diverse set of scene configurations and properties. This process is incredibly time-consuming, and it is challenging to ensure that the captured data distribution maps well to the target domain of an application scenario. Recently, synthetic data has emerged as a way to address both of these issues. However, existing approaches either require human experts to manually tune each scene property or use automatic methods that provide little to no control; this requires rendering large amounts of random data variations, which is slow and is often suboptimal for the target domain. We present the first fully differentiable synthetic data pipeline that uses Neural Radiance Fields (NeRFs) in a closed-loop with a target application's loss function. Our approach generates data on-demand, with no human labor, to maximize accuracy for a target task. We illustrate the effectiveness of our method on synthetic and real-world object detection tasks. We also introduce a new "YCB-in-the-Wild" dataset and benchmark that provides a test scenario for object detection with varied poses in real-world environments.

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。

↑