UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving
This work provides a comprehensive benchmark for researchers in autonomous driving to evaluate occupancy models more robustly, though it is incremental as it builds on existing datasets and methods.
The authors tackled the problem of evaluating occupancy forecasting and prediction in autonomous driving by introducing UniOcc, a unified benchmark and toolkit that unifies data from multiple real-world datasets and simulators, and they demonstrated that large-scale, diverse training data and explicit flow information significantly enhance performance.
We introduce UniOcc, a comprehensive, unified benchmark and toolkit for occupancy forecasting (i.e., predicting future occupancies based on historical information) and occupancy prediction (i.e., predicting current-frame occupancy from camera images. UniOcc unifies the data from multiple real-world datasets (i.e., nuScenes, Waymo) and high-fidelity driving simulators (i.e., CARLA, OpenCOOD), providing 2D/3D occupancy labels and annotating innovative per-voxel flows. Unlike existing studies that rely on suboptimal pseudo labels for evaluation, UniOcc incorporates novel evaluation metrics that do not depend on ground-truth labels, enabling robust assessment on additional aspects of occupancy quality. Through extensive experiments on state-of-the-art models, we demonstrate that large-scale, diverse training data and explicit flow information significantly enhance occupancy prediction and forecasting performance. Our data and code are available at https://uniocc.github.io/.