发表机构
Nankai University; Momenta; KargoBot（南开大学; Momenta（魔门塔）; 智加科技）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对基于点的占据预测与自动驾驶所需稠密体素占据的不匹配问题，提出OPUS-V2框架，通过点-体素变换模块和特征-占据解耦设计，在两个数据集上实现了先进性能并保持实时运行。
AI 中文摘要
基于点的占据预测范式通过稀疏建模3D空间，在精度与效率之间取得了颇具吸引力的平衡。然而，其预测结果与自动驾驶系统所需的稠密体素占据要求存在固有不匹配，因此在训练和推理阶段需要人工设计的启发式规则，这限制了最终性能。为克服这些局限，我们提出了OPUS-V2，这是一个基于开创性OPUS（使用稀疏集的占据预测）点基方法的新型框架。OPUS-V2在解码器后集成了轻量级点-体素变换（PVT）模块，可自适应地将稀疏预测映射到稠密体素空间，消除了次优操作并提高了模型精度。此外，我们的架构将特征生成与占据生成分离开来，使OPUS-V2能够适配任意占据分辨率。OPUS-V2在Occ3D数据集上达到了44.0的先进射线交并比（rayIoU），在更具挑战性的OpenOccupancy数据集上，取得了有竞争力的16.4平均交并比（mIoU），同时以20.6 FPS的帧率实时运行。
英文摘要
The point-based occupancy prediction paradigm has achieved an attractive trade-off between accuracy and efficiency by modeling 3D space sparsely. However, its predictions inherently mismatch the dense voxel-based occupancy required by self-driving systems, necessitating hand-crafted heuristics during training and inference that limit final performance. To overcome these limitations, we propose OPUS-V2, a novel framework built upon the pioneering OPUS (occupancy prediction using a sparse set) point-based approach. OPUS-V2 incorporates a lightweight point-voxel transformation (PVT) module behind the decoder to adaptively map sparse predictions into the dense voxel space, eliminating the need for suboptimal operations and improving model accuracy. Furthermore, our architecture decouples feature and occupancy generation processes, allowing OPUS-V2 to adapt to arbitrary occupancy resolutions. OPUS-V2 achieves a state-of-the-art rayIoU of 44.0 on the Occ3D dataset. On the more challenging OpenOccupancy dataset, it attains a competitive 16.4 mIoU while running in real time at 20.6 FPS.
