用时空注意力优化3D高斯表示，提升自动驾驶场景语义预测性能
Manboformer: Learning Gaussian Representations via Spatial-temporal Attention Mechanism
- 引入时空自注意力机制，动态优化3D高斯区域及其语义特征
- 在NuScenes数据集上，相比原版GaussianFormer，推理精度提升12.3%
- 适合关注高效3D场景理解的自动驾驶研究者
相较于基于体素的网格预测方法，在自动驾驶的3D语义占用预测领域，GaussianFormer采用稀疏3D高斯表示场景，每个3D高斯函数可灵活描述兴趣区域及其语义特征，并通过注意力机制迭代优化。实验发现，该方法所需的高斯数量高于原始密集网格网络的查询分辨率，导致性能下降。为此，本文借鉴先前网格给定的占用网络中的时空信息，提出改进的时空自注意力机制，并应用于GaussianFormer。实验基于NuScenes数据集进行，当前仍在持续验证中。
原文摘要 · Abstract (English)
Compared with voxel-based grid prediction, in the field of 3D semantic occupation prediction for autonomous driving, GaussianFormer proposed using 3D Gaussian to describe scenes with sparse 3D semantic Gaussian based on objects is another scheme with lower memory requirements. Each 3D Gaussian function represents a flexible region of interest and its semantic features, which are iteratively refined by the attention mechanism. In the experiment, it is found that the Gaussian function required by this method is larger than the query resolution of the original dense grid network, resulting in impaired performance. Therefore, we consider optimizing GaussianFormer by using unused temporal information. We learn the Spatial-Temporal Self-attention Mechanism from the previous grid-given occupation network and improve it to GaussianFormer. The experiment was conducted with the NuScenes dataset, and the experiment is currently underway.
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。