将稀疏点预测精准映射到稠密体素，提升自动驾驶占用预测效率与精度
OPUS-V2: Bridging the Gap between Sparse Points and Dense Voxels
- 用轻量级点-体素转换模块，自动将稀疏预测转为稠密体素
- 在Occ3D上达44.0的rayIoU，OpenOccupancy上16.4 mIoU，实时运行20.6 FPS
- 无需手工规则，适配任意分辨率，适合自动驾驶感知系统
基于点的占用预测范式通过稀疏建模3D空间，在精度与效率之间取得了良好平衡。然而，其预测结果与自动驾驶系统所需的稠密体素占用存在本质不匹配，导致训练和推理中需依赖手工设计的启发式规则，限制了最终性能。为此，我们提出OPUS-V2，一个建立在开创性OPUS（基于稀疏点集的占用预测）方法之上的新框架。OPUS-V2在解码器后引入轻量级点-体素转换（PVT）模块，自适应地将稀疏预测映射至稠密体素空间，消除次优操作，提升模型精度。此外，该架构解耦特征与占用生成过程，使OPUS-V2可适配任意占用分辨率。在Occ3D数据集上达到44.0的rayIoU，在更具挑战性的OpenOccupancy数据集上取得16.4 mIoU，且以20.6 FPS实现实时运行。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。