OccProphet：通过观测器-预测器-精炼器框架推动纯相机4D占用预测的效率边界
OccProphet: Pushing Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with Observer-Forecaster-Refiner Framework
AI总结：
针对纯相机4D占用预测计算成本高、难以在边缘部署的问题，提出由观测器、预测器、精炼器组成的OccProphet框架，在多个数据集上实现精度提升的同时大幅降低计算量、加快推理速度。
摘要：
预测复杂交通环境的变化对自动驾驶的安全性至关重要。近期占用预测领域的进展已能通过观测历史2D图像来预测驾驶环境中的未来3D占用状态。然而，高计算需求导致占用预测在训练和推理阶段效率较低，阻碍了其在边缘智能体上部署的可行性。本文提出了一种名为OccProphet的新型框架，能以显著更低的计算需求高效且有效地学习占用预测，同时提升预测精度。OccProphet由三个轻量级组件构成：观测器（Observer）、预测器（Forecaster）和精炼器（Refiner）。观测器通过提出的带三重注意力融合的高效4D聚合（Efficient 4D Aggregation with Tripling-Attention Fusion）方法，从3D多帧体素中提取时空特征，而预测器和精炼器则有条件地预测并精炼未来占用推断结果。在nuScenes、Lyft-Level5和nuScenes-Occupancy数据集上的实验结果表明，OccProphet兼具训练友好性和推理友好性。与当前最优的Cam4DOcc相比，OccProphet降低了58%~78%的计算成本，速度提升2.6倍。此外，它的预测精度相对高出4%~18%。代码和模型已公开于https://github.com/JLChen-C/OccProphet。
英文摘要：
Predicting variations in complex traffic environments is crucial for the safety of autonomous driving. Recent advancements in occupancy forecasting have enabled forecasting future 3D occupied status in driving environments by observing historical 2D images. However, high computational demands make occupancy forecasting less efficient during training and inference stages, hindering its feasibility for deployment on edge agents. In this paper, we propose a novel framework, i.e., OccProphet, to efficiently and effectively learn occupancy forecasting with significantly lower computational requirements while improving forecasting accuracy. OccProphet comprises three lightweight components: Observer, Forecaster, and Refiner. The Observer extracts spatio-temporal features from 3D multi-frame voxels using the proposed Efficient 4D Aggregation with Tripling-Attention Fusion, while the Forecaster and Refiner conditionally predict and refine future occupancy inferences. Experimental results on nuScenes, Lyft-Level5, and nuScenes-Occupancy datasets demonstrate that OccProphet is both training- and inference-friendly. OccProphet reduces 58\%$\sim$78\% of the computational cost with a 2.6$\times$ speedup compared with the state-of-the-art Cam4DOcc. Moreover, it achieves 4\%$\sim$18\% relatively higher forecasting accuracy. Code and models are publicly available at https://github.com/JLChen-C/OccProphet.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
