L3DR: 3D-aware LiDAR Diffusion and Rectification
This work addresses the generation of realistic 3D LiDAR data for autonomous driving and robotics, representing an incremental improvement by rectifying artifacts in existing diffusion models.
The paper tackled the problem of 3D geometry realism in range-view LiDAR diffusion, which often suffers from artifacts like depth bleeding and wavy surfaces, and resulted in a framework that achieves state-of-the-art generation with superior geometry-realism across multiple benchmarks.
Range-view (RV) based LiDAR diffusion has recently made huge strides towards 2D photo-realism. However, it neglects 3D geometry realism and often generates various RV artifacts such as depth bleeding and wavy surfaces. We design L3DR, a 3D-aware LiDAR Diffusion and Rectification framework that can regress and cancel RV artifacts in 3D space and restore local geometry accurately. Our theoretical and empirical analysis reveals that 3D models are inherently superior to 2D models in generating sharp and authentic boundaries. Leveraging such analysis, we design a 3D residual regression network that rectifies RV artifacts and achieves superb geometry realism by predicting point-level offsets in 3D space. On top of that, we design a Welsch Loss that helps focus on local geometry and ignore anomalous regions effectively. Extensive experiments over multiple benchmarks including KITTI, KITTI360, nuScenes and Waymo show that the proposed L3DR achieves state-of-the-art generation and superior geometry-realism consistently. In addition, L3DR is generally applicable to different LiDAR diffusion models with little computational overhead.