Score: 3

PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Models

Published: August 23, 2025 | arXiv ID: 2508.17050v1

By: Xianjing Cheng , Lintai Wu , Zuowen Wang and more

Potential Business Impact:

Makes 3D maps of outdoor places more detailed.

Business Areas:
Image Recognition Data and Analytics, Software

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.

Country of Origin
🇨🇳 🇭🇰 Hong Kong, China

Repos / Data Links

Page Count
15 pages

Category
Computer Science:
CV and Pattern Recognition