UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yuping, Huang, Xiangyu, Sun, Xiaokang, Yan, Mingxuan, Xing, Shuo, Tu, Zhengzhong, Li, Jiachen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915445479571456
author Wang, Yuping
Huang, Xiangyu
Sun, Xiaokang
Yan, Mingxuan
Xing, Shuo
Tu, Zhengzhong
Li, Jiachen
author_facet Wang, Yuping
Huang, Xiangyu
Sun, Xiaokang
Yan, Mingxuan
Xing, Shuo
Tu, Zhengzhong
Li, Jiachen
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2503_24381
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving
Wang, Yuping
Huang, Xiangyu
Sun, Xiaokang
Yan, Mingxuan
Xing, Shuo
Tu, Zhengzhong
Li, Jiachen
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Multiagent Systems
Robotics
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/.
title UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Multiagent Systems
Robotics
url https://arxiv.org/abs/2503.24381