提出几何感知的稀疏表示，提升语义占用预测精度与速度。
SparseOcc++: Geometry-Aware Sparse Latent Representation for Semantic Occupancy Prediction
- 分离场景补全与语义分割，避免空区域误激活。
- 在nuScenes上提升IoU 2.3点，速度比SparseOcc快3.9倍。
- 适合需要高效高精度3D感知的自动驾驶系统。
基于视觉的3D语义占用预测对自动驾驶至关重要，但密集体素表示在大量空区域浪费计算资源，而鸟瞰图（BEV）和顶视图（TPV）投影会损失精细3D结构。完全稀疏表示是可行替代方案，但现有方法（如SparseOcc）将场景补全与语义预测混杂，盲目将高维特征传播至空区域并进行体素级分类，导致过度激活、计算开销大且几何模糊。本文提出SparseOcc++，一种几何感知的稀疏框架，显式解耦场景补全与语义分割。通过场景补全场（SCF）在稀疏锚定体素上进行符号距离回归实现补全；结合正交分解与离散距离学习以稳健建模复杂室外几何。几何引导传播模块将SCF转化为完整体积场景，并仅在几何验证区域执行语义分割。实验表明，SparseOcc++在nuScenes上实现新最优：相比SparseOcc提升IoU 2.3点，速度提升3.9倍；在SemanticKITTI上相较OccFormer提速5.9倍。
原文摘要 · Abstract (English)
Vision-based 3D semantic occupancy prediction is essential for autonomous driving, yet dense voxel representations waste computation on largely empty space, while BEV and TPV projections compromise fine-grained 3D structure. Fully sparse representations offer an attractive alternative, but existing methods, including SparseOcc, entangle scene completion with semantic prediction by indiscriminately propagating high-dimensional features into empty regions and applying voxel-wise classification. This creates excessive activations, computational overhead, and geometric ambiguity. We present SparseOcc++, a geometry-aware sparse framework that explicitly decouples scene completion from semantic segmentation. SparseOcc++ reformulates completion as signed-distance regression on sparse anchor voxels through a scene completion field (SCF). To model complex outdoor geometry robustly, it combines orthogonal decomposition with discretized distance learning. A geometry-guided propagation module then converts the SCF into a complete volumetric scene and restricts semantic segmentation to geometrically verified regions. Experiments establish new state of the art: SparseOcc++ improves IoU by 2.3 points and is 3.9x faster than SparseOcc on nuScenes, while achieving a 5.9x speedup over OccFormer on SemanticKITTI.
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。