SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark

TL;DR

SEED4D introduces a customizable synthetic data generator and large-scale datasets for egocentric and exocentric 3D/4D reconstruction in autonomous driving, enabling improved model training and evaluation.

Contribution

It provides the first open-source, flexible synthetic data generator and extensive datasets for dynamic multi-view urban scene reconstruction in autonomous driving.

Findings

Created 212k static vehicle images from 2k scenes.

Generated 16.8M dynamic images from 10k trajectories.

Facilitates development of 3D/4D reconstruction models.

Abstract

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/.