LidarDM: Generative LiDAR Simulation in a Generated World

1 code implementation • 3 Apr 2024 • Vlas Zyrianov, Henry Che, Zhijian Liu, Shenlong Wang

We present LidarDM, a novel LiDAR generative model capable of producing realistic, layout-aware, physically plausible, and temporally coherent LiDAR videos.

Autonomous Driving Point Cloud Generation

MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models

no code implementations • ICCV 2023 • Xiyue Zhu, Vlas Zyrianov, Zhijian Liu, Shenlong Wang

Despite tremendous advancements in bird's-eye view (BEV) perception, existing models fall short in generating realistic and coherent semantic map layouts, and they fail to account for uncertainties arising from partial sensor information (such as occlusion or limited coverage).

Learning to Generate Realistic LiDAR Point Clouds

1 code implementation • 8 Sep 2022 • Vlas Zyrianov, Xiyue Zhu, Shenlong Wang

We present LiDARGen, a novel, effective, and controllable generative model that produces realistic LiDAR point cloud sensory readings.

Denoising Point Cloud Generation