Implicit Neural Compression of Point Clouds
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 260-275
Abstract
Point clouds have gained prominence across numerous applications due to their ability to accurately represent 3D objects and scenes. However, efficiently compressing unstructured, high-precision point cloud data remains a significant challenge. In this paper, we propose NeRC3, a novel point cloud compression framework that leverages implicit neural representations (INRs) to encode both geometry and attributes of dense point clouds. Our approach employs two coordinate-based neural networks: one maps spatial coordinates to voxel occupancy, while the other maps occupied voxels to their attributes, thereby implicitly representing the geometry and attributes of a voxelized point cloud. The encoder quantizes and compresses network parameters alongside auxiliary information required for reconstruction, while the decoder reconstructs the original point cloud by inputting voxel coordinates into the neural networks. Furthermore, we extend our method to dynamic point cloud compression through techniques that reduce temporal redundancy, including a 4D spatio-temporal representation termed 4D-NeRC3. Experimental results validate the effectiveness of our approach: For static point clouds, NeRC3 outperforms octree-based G-PCC standard and existing INR-based methods. For dynamic point clouds, 4D-NeRC3 achieves superior geometry compression performance compared to the latest G-PCC and V-PCC standards, while matching state-of-the-art learning-based methods. It also demonstrates competitive performance in joint geometry and attribute compression.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2024YFE0200802)
- National Natural Science Foundation of China (62293481)
- National Natural Science Foundation of China (62571487)
- National Natural Science Foundation of China (62201505)
- National Natural Science Foundation of China (62394292)
- Zhejiang Provincial Natural Science Foundation of China (LZ25F010001)
- Zhejiang Provincial Key Research and Development Program (2023C01021)
- Zhejiang Key Laboratory of Multimodal Communication Networks and Intelligent Information Processing; and in part by the Fundamental Research Funds for the Central Universities (226-2024-00069)
- HKU Seed Fund for basic research (2501250652)
This publication has 54 references indexed in Scilit:
- An end-to-end dynamic point cloud geometry compression in latent spaceDisplays, 2023
- Implicit Neural Representations for Image Compression2022
- 3DAC: Learning Attribute Compression for Point Clouds2022
- Local Implicit Grid Representations for 3D Scenes2020
- An overview of ongoing point cloud compression standardization activities: video-based (V-PCC) and geometry-based (G-PCC)APSIPA Transactions on Signal and Information Processing, 2020
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation2019
- Learning Implicit Fields for Generative Shape Modeling2019
- Occupancy Networks: Learning 3D Reconstruction in Function Space2019
- DVC: An End-To-End Deep Video Compression Framework2019
- Deep Residual Learning for Image Recognition2016