MV2：用于新视角合成的多视角多车辆驾驶数据集
MV2: Multi-View Multi-Vehicle Driving Dataset for Novel View Synthesis
另 2 家 · 查看机构详情
- International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）
- King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）
- IIT, National Centre for Scientific Research “Demokritos”（德谟克利特国家科学研究中心 IIT）
- Adobe MDSR, India（奥多比印度MDSR部门）
- Indian Institute of Science Education and Research, Thiruvananthapuram（特里凡得琅印度科学教育与研究学院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对驾驶场景新视角合成的难题，提出含50个场景12000张图像的MV2多车辆数据集，经严格配准验证，基准测试显示视角差异增大NVS性能下降，前馈位姿估计器弱于优化方法。
中文摘要 AI 辅助
可微渲染技术推动了新视角合成（NVS）的发展，但将其应用于真实世界的驾驶场景仍存在困难，原因包括采集视角稀疏、存在动态物体以及多轨迹数据有限。本文介绍了用于评估动态城市场景中大幅视角变化下NVS模型的多视角多车辆（MV2）数据集与基准。MV2包含来自汽车、踏板车和无人机的同步采集数据，三者遵循不同但同步的轨迹。在某一车辆的相机流上训练NVS方法，在另一车辆上进行测试，可实现比现有单轨迹数据集大得多的视角变化下的评估。所有序列通过运动恢复结构（SfM）配准，相机位姿通过手动像素级对应标注验证，共得到50个高质量场景，含12000张图像。对近期NVS和相机位姿估计方法的基准测试显示，NVS性能随视角差异增大而下降，前馈位姿估计器明显落后于基于优化的方法，表明MV2是驾驶场景中NVS的严格测试平台。该数据集、基准协议及项目资源可在指定网址获取。
英文摘要
Differentiable rendering has advanced novel view synthesis (NVS), yet applying it to real-world driving remains difficult due to sparse capture viewpoints, dynamic objects, and limited multi-trajectory data. We introduce the Multi-View Multi-Vehicle (MV2) dataset and benchmark for evaluating NVS models under large viewpoint changes in dynamic urban scenes. MV2 features synchronized captures from a car, scooter, and drone, each following distinct yet synchronized trajectories. Training NVS methods on one vehicle's camera stream and testing on another enables evaluation under substantially larger viewpoint variations than existing single-trajectory datasets. All sequences are registered via Structure-from-Motion and camera poses verified using manual pixel-level correspondence annotations, yielding 50 high-quality scenes with 12000 images. Benchmarking recent NVS and camera pose estimation methods shows that NVS performance degrades with increasing viewpoint disparity, and that feed-forward pose estimators notably lag behind optimization-based approaches, highlighting MV2 as a rigorous testbed for NVS in driving. The dataset, benchmark protocol, and project resources are available at https://mv2-dataset.github.io/.
