PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Models
By: Xianjing Cheng , Lintai Wu , Zuowen Wang and more
Potential Business Impact:
Makes 3D maps of outdoor places more detailed.
Accurate 3D scene understanding in outdoor environments heavily relies on high-quality point clouds. However, LiDAR-scanned data often suffer from extreme sparsity, severely hindering downstream 3D perception tasks. Existing point cloud upsampling methods primarily focus on individual objects, thus demonstrating limited generalization capability for complex outdoor scenes. To address this issue, we propose PVNet, a diffusion model-based point-voxel interaction framework to perform LiDAR point cloud upsampling without dense supervision. Specifically, we adopt the classifier-free guidance-based DDPMs to guide the generation, in which we employ a sparse point cloud as the guiding condition and the synthesized point clouds derived from its nearby frames as the input. Moreover, we design a voxel completion module to refine and complete the coarse voxel features for enriching the feature representation. In addition, we propose a point-voxel interaction module to integrate features from both points and voxels, which efficiently improves the environmental perception capability of each upsampled point. To the best of our knowledge, our approach is the first scene-level point cloud upsampling method supporting arbitrary upsampling rates. Extensive experiments on various benchmarks demonstrate that our method achieves state-of-the-art performance. The source code will be available at https://github.com/chengxianjing/PVNet.
Similar Papers
Multimodal Point Cloud Semantic Segmentation With Virtual Point Enhancement
CV and Pattern Recognition
Makes self-driving cars see small things better.
A Unified Voxel Diffusion Module for Point Cloud 3D Object Detection
CV and Pattern Recognition
Helps cars see objects better in 3D.
LiDAR Point Cloud Image-based Generation Using Denoising Diffusion Probabilistic Models
CV and Pattern Recognition
Makes self-driving cars see better in bad weather.