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 2011.14488cs.CV
收藏

自监督Real-to-Sim场景生成

Self-Supervised Real-to-Sim Scene Generation

NVIDIA(英伟达)

Aayush Prakash, Shoubhik Debnath, Jean-Francois Lafleche, Eric Cameracci, Gavriel State, Stan Birchfield, Marc T. Law

摘要:

合成数据正在成为有监督深度学习可扩展性问题的一个有前途的解决方案,特别是当真实数据难以获取或难以注释时。然而,当领域专家不得不手动地、煞费苦心地监督该过程时,合成数据生成本身可能是极其昂贵的。此外,由于域间隙,在合成数据上训练的神经网络通常在真实数据上表现不佳。为了解决这些挑战,我们提出了Sim 2SG,一种自监督自动场景生成技术,用于匹配真实数据的分布。重要的是,Sim 2SG不需要来自真实世界数据集的监督,从而使其适用于难以获得此类注释的情况。Sim 2SG旨在通过匹配真实数据的内容以及匹配源域和目标域中的特征来弥合内容和外观之间的差距。我们选择场景图(SG)生成作为下游任务,由于有限的可用性标记的数据集。实验表明,在几个合成数据集以及真实世界的KITTI数据集上,在定性和定量减少域差距方面,领先的基线有了显着的改进。

英文摘要:

Synthetic data is emerging as a promising solution to the scalability issue of supervised deep learning, especially when real data are difficult to acquire or hard to annotate. Synthetic data generation, however, can itself be prohibitively expensive when domain experts have to manually and painstakingly oversee the process. Moreover, neural networks trained on synthetic data often do not perform well on real data because of the domain gap. To solve these challenges, we propose Sim2SG, a self-supervised automatic scene generation technique for matching the distribution of real data. Importantly, Sim2SG does not require supervision from the real-world dataset, thus making it applicable in situations for which such annotations are difficult to obtain. Sim2SG is designed to bridge both the content and appearance gaps, by matching the content of real data, and by matching the features in the source and target domains. We select scene graph (SG) generation as the downstream task, due to the limited availability of labeled datasets. Experiments demonstrate significant improvements over leading baselines in reducing the domain gap both qualitatively and quantitatively, on several synthetic datasets as well as the real-world KITTI dataset.

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。

↑