KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D
复制标题
DOI：
10.1109/tpami.2022.3179507
复制
发表时间：
2023-03-01
影响因子：
23.6
通讯作者：
Geiger, Andreas
中科院分区：
文献类型：
--
作者：
Liao, Yiyi;Xie, Jun;Geiger, Andreas
在过去的几十年里，人工智能的几个主要子领域，包括计算机视觉、图形学和机器人技术，在很大程度上相互独立地取得了进展。然而，最近，社会各界认识到，要想实现自动驾驶汽车等强大的智能系统，需要在不同领域做出协调一致的努力。这促使我们开发了流行的Kitti数据集的继承者Kitti-360。KITTI-360是一个郊区驾驶数据集，它包括更丰富的输入模式、全面的语义实例注释和准确的定位，以促进视觉、图形和机器人技术的交叉研究。为了有效地标注，我们创建了一个工具来使用边界基元来标记3D场景，并开发了一个模型来将这些信息转换到2D图像域中，从而产生了超过15万个图像和1B个3D点，并且在2D和3D之间具有一致的语义实例标注。此外，我们为与移动感知相关的几个任务建立了基准和基线，包括来自同一数据集上的计算机视觉、图形学和机器人学的问题，例如语义场景理解、新颖的视图合成和语义SLAM。KITTI-360将使这些研究领域的交叉点取得进展，从而有助于解决当今的重大挑战之一：开发完全自动驾驶系统。
For the last few decades, several major subfields of artificial intelligence including computer vision, graphics, and robotics have progressed largely independently from each other. Recently, however, the community has realized that progress towards robust intelligent systems such as self-driving cars requires a concerted effort across the different fields. This motivated us to develop KITTI-360, successor of the popular KITTI dataset. KITTI-360 is a suburban driving dataset which comprises richer input modalities, comprehensive semantic instance annotations and accurate localization to facilitate research at the intersection of vision, graphics and robotics. For efficient annotation, we created a tool to label 3D scenes with bounding primitives and developed a model that transfers this information into the 2D image domain, resulting in over 150k images and 1B 3D points with coherent semantic instance annotations across 2D and 3D. Moreover, we established benchmarks and baselines for several tasks relevant to mobile perception, encompassing problems from computer vision, graphics, and robotics on the same dataset, e.g., semantic scene understanding, novel view synthesis and semantic SLAM. KITTI-360 will enable progress at the intersection of these research areas and thus contribute towards solving one of today's grand challenges: the development of fully autonomous self-driving systems.