XLD：用于基准测试新型驾驶视图合成的跨车道数据集
XLD: A Cross-Lane Dataset for Benchmarking Novel Driving View Synthesis
AI总结：
本文提出跨车道数据集XLD，通过偏离训练轨迹1-4米的合成测试图像，建立首个面向自动驾驶仿真的新型视图合成基准，并揭示现有NVS方法在跨车道与闭环仿真中的不足。
摘要：
通过仿真对自动驾驶系统进行全面测试对于确保自动驾驶车辆的安全性至关重要。这需要生成超越真实世界数据采集局限的安全关键场景，因为其中许多场景在公共道路上十分罕见或很少遇到。然而，评估大多数现有新型视图合成（NVS）方法依赖于从训练数据中零星采样图像帧，并将渲染图像与真值图像进行比较。遗憾的是，这种评估协议无法满足闭环仿真的实际需求。具体而言，真实应用要求具备渲染超出原始轨迹的新型视图（例如跨车道视图）的能力，而这些视图在现实世界中难以采集。为了解决这一问题，本文提出了一个用于新型驾驶视图合成评估的合成数据集，该数据集专为自动驾驶仿真而设计。这一独特的数据集包含通过偏离训练轨迹1-4米所采集的测试图像。它由六个序列组成，涵盖不同的时间和天气条件。每个序列包含450张训练图像、120张测试图像，以及它们对应的相机位姿和内参。利用这一新型数据集，我们建立了首个真实基准，用于在仅前视和多相机设置下评估现有NVS方法。实验发现凸显了当前方法的显著差距，揭示了它们在满足跨车道或闭环仿真的严苛前提条件方面能力不足。
英文摘要：
Comprehensive testing of autonomous systems through simulation is essential to ensure the safety of autonomous driving vehicles. This requires the generation of safety-critical scenarios that extend beyond the limitations of real-world data collection, as many of these scenarios are rare or rarely encountered on public roads. However, evaluating most existing novel view synthesis (NVS) methods relies on sporadic sampling of image frames from the training data, comparing the rendered images with ground-truth images. Unfortunately, this evaluation protocol falls short of meeting the actual requirements in closed-loop simulations. Specifically, the true application demands the capability to render novel views that extend beyond the original trajectory (such as cross-lane views), which are challenging to capture in the real world. To address this, this paper presents a synthetic dataset for novel driving view synthesis evaluation, which is specifically designed for autonomous driving simulations. This unique dataset includes testing images captured by deviating from the training trajectory by $1-4$ meters. It comprises six sequences that cover various times and weather conditions. Each sequence contains $450$ training images, $120$ testing images, and their corresponding camera poses and intrinsic parameters. Leveraging this novel dataset, we establish the first realistic benchmark for evaluating existing NVS approaches under front-only and multicamera settings. The experimental findings underscore the significant gap in current approaches, revealing their inadequate ability to fulfill the demanding prerequisites of cross-lane or closed-loop simulation.
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。
