用极坐标提升3D语义占据预测，减少畸变并提高精度
PVP: Polar Representation Boost for 3D Semantic Occupancy Prediction
- 采用极坐标系结合全局传播与平面分解卷积
- 在OpenOccupancy上mIoU和IoU显著优于现有方法
- 适合做3D场景理解的科研人员和工程师参考
近期基于极坐标的3D感知表示展现出潜力。与笛卡尔方法相比，极坐标网格在近距离区域能更好保留细节，并覆盖更大范围，但存在因非均匀划分导致的特征畸变问题。为此，我们提出极坐标体素占据预测器（PVP），一种新型3D多模态预测模型，运行于极坐标系。PVP包含两个关键设计：全局表征传播（GRP）模块，将全局空间信息融入3D体素；平面分解卷积（PD-Conv），将3D畸变简化为2D卷积。这些创新使PVP在OpenOccupancy数据集上实现显著的mIoU与IoU提升。
原文摘要 · Abstract (English)
Recently, polar coordinate-based representations have shown promise for 3D perceptual tasks. Compared to Cartesian methods, polar grids provide a viable alternative, offering better detail preservation in nearby spaces while covering larger areas. However, they face feature distortion due to non-uniform division. To address these issues, we introduce the Polar Voxel Occupancy Predictor (PVP), a novel 3D multi-modal predictor that operates in polar coordinates. PVP features two key design elements to overcome distortion: a Global Represent Propagation (GRP) module that integrates global spatial data into 3D volumes, and a Plane Decomposed Convolution (PD-Conv) that simplifies 3D distortions into 2D convolutions. These innovations enable PVP to outperform existing methods, achieving significant improvements in mIoU and IoU metrics on the OpenOccupancy dataset.
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。