生成驾驶场景的多视角4D数据，支持3D/4D重建模型训练。
SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark
- 自定义生成时空多视角合成数据，适配主流自动驾驶数据集相机配置。
- 构建212000张静态图像和1680万张动态图像数据集，含车内外视角与激光雷达。
- 开源工具链支持研究者快速生成逼真多视角驾驶数据，适合3D/4D重建任务。
用于自指视角3D和4D重建的模型，包括少样本插值与外推设置，可受益于外部视角图像提供的监督信号。现有数据集缺乏复杂、动态且多视角的数据混合。为促进自动驾驶场景下3D与4D重建方法的发展，我们提出Synthetic Ego--Exo Dynamic 4D（SEED4D）数据生成器与数据集。该系统提供可定制、易用的时空多视角数据生成工具，支持常见于NuScenes、KITTI360和Waymo数据集的相机布局。此外，SEED4D包含两个大规模多视角合成城市场景数据集：静态（3D）数据集包含212,000张来自2,000个场景的车内外视角图像；动态（4D）数据集包含1680万张图像，来自10,000条轨迹，每条轨迹在100个时间点采样，包含自指视角图像、外部视角图像和激光雷达数据。数据集与生成器开源，详见https://seed4d.github.io/。
原文摘要 · Abstract (English)
Models for egocentric 3D and 4D reconstruction, including few-shot interpolation and extrapolation settings, can benefit from having images from exocentric viewpoints as supervision signals. No existing dataset provides the necessary mixture of complex, dynamic, and multi-view data. To facilitate the development of 3D and 4D reconstruction methods in the autonomous driving context, we propose a Synthetic Ego--Exo Dynamic 4D (SEED4D) data generator and dataset. We present a customizable, easy-to-use data generator for spatio-temporal multi-view data creation. Our open-source data generator allows the creation of synthetic data for camera setups commonly used in the NuScenes, KITTI360, and Waymo datasets. Additionally, SEED4D encompasses two large-scale multi-view synthetic urban scene datasets. Our static (3D) dataset encompasses 212k inward- and outward-facing vehicle images from 2k scenes, while our dynamic (4D) dataset contains 16.8M images from 10k trajectories, each sampled at 100 points in time with egocentric images, exocentric images, and LiDAR data. The datasets and the data generator can be found at https://seed4d.github.io/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。