邁向實時且自適應的LiDAR場景補全

摘要

光達場景補全是自動駕駛中3D感知的關鍵組成部分，場景必須即時完成才能用於下游任務。現有方法通常遵循初始化-精煉範式，首先建構場景的粗略初始化，然後將其精煉為完整的3D幾何結構。生成式模型較慢，因為它們將隨機高斯雜訊迭代地精煉成場景，而非生成式方法則以固定雜訊尺度擾動部分場景，這限制了大間隙與遮擋區域的覆蓋範圍，並且需要針對每種新的感測器配置手動重新校準。我們提出RapidLiDAR，一種將初始化本身視為學習式、資料驅動元件的光達場景補全方法。我們提出一個自適應初始化模組，為每個部分輸入點預測空間變化的位移，將部分觀測擴展為適應局部幾何的粗略場景初始化，而無需手動雜訊調整。為了將此粗略初始化精煉為完整且連貫的場景，我們另提出一個多尺度重建模組，透過查詢從輸入掃描建構的多尺度3D體素與2D BEV特徵圖，進一步精煉點位置。透過以基於體素與BEV的特徵提取取代諸如最遠點採樣和k近鄰搜尋等點鄰域運算，我們的架構更快，且在設計上能處理不同的輸入解析度。在SemanticKITTI和KITTI-360上的實驗表明，我們的方法在補全效能上與現有最先進方法相當，同時在0.1秒內完成整個場景，比先前最快的方法快2.3倍。這匹配典型車用光達感測器的10 Hz擷取率，朝向即時光達場景補全邁進一步。

English

LiDAR scene completion is a key component of 3D perception in autonomous driving, where the scene must be completed in real time to be usable in downstream tasks. Existing approaches typically follow an initialize-and-refine paradigm, in which a coarse initialization of the scene is first constructed, then refined into complete 3D geometry. Generative models are slower because they iteratively refine random Gaussian noise into the scene, while non-generative methods perturb the partial scene with a fixed noise scale, which limits coverage of large gaps and occluded regions and requires manual recalibration for each new sensor configuration. We present RapidLiDAR, a LiDAR scene completion method that treats the initialization itself as a learned, data-driven component. We propose an adaptive initialization module that predicts a spatially varying displacement for each partial input point, expanding the partial observations into a coarse scene initialization adapted to the local geometry, without requiring manual noise tuning. To refine this coarse initialization into a complete and coherent scene, we additionally propose a multi-scale reconstruction module that further refines point positions by querying multi-scale 3D voxel and 2D BEV feature maps constructed from the input scan. By replacing point-neighborhood operators such as farthest point sampling and k-nearest neighbor search with voxel- and BEV-based feature extraction, our architecture is faster and can handle different input resolutions by design. Experiments on SemanticKITTI and KITTI-360 show that our method achieves completion performance on par with the state of the art while completing a full scene in 0.1 seconds, which is 2.3 times faster than the fastest prior method. This matches the 10 Hz acquisition rate of typical automotive LiDAR sensors, taking a step toward real-time LiDAR scene completion.