Fast Inter-frame Motion Prediction for Compressed Dynamic Point Cloud Attribute Enhancement
DOI:
https://doi.org/10.1609/aaai.v38i4.28162Keywords:
CV: Motion & Tracking, CV: Vision for Robotics & Autonomous DrivingAbstract
Recent years have witnessed the success of deep learning methods in quality enhancement of compressed point cloud. However, existing methods focus on geometry and attribute enhancement of single-frame point cloud. This paper proposes a novel compressed quality enhancement method for dynamic point cloud (DAE-MP). Specifically, we propose a fast inter-frame motion prediction module (IFMP) to explicitly estimate motion displacement and achieve inter-frame feature alignment. To maintain motion continuity between consecutive frames, we propose a motion consistency loss for supervised learning. Furthermore, a frequency component separation and fusion module is designed to extract rich frequency features adaptively. To the best of our knowledge, the proposed method is the first deep learning-based work to enhance the quality for compressed dynamic point cloud. Experimental results show that the proposed method can greatly improve the quality of compressed dynamic point cloud and provide a fast and efficient motion prediction plug-in for large-scale point cloud. For dynamic point cloud attribute with severely compressed artifact, our proposed DAE-MP method achieves up to 0.52dB (PSNR) performance gain. Moreover, the proposed IFMP module has a certain real-time processing ability for calculating the motion offset between dynamic point cloud frame.Downloads
Published
2024-03-24
How to Cite
Liu, W., Gao, W., & Mu, X. (2024). Fast Inter-frame Motion Prediction for Compressed Dynamic Point Cloud Attribute Enhancement. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 3720-3728. https://doi.org/10.1609/aaai.v38i4.28162
Issue
Section
AAAI Technical Track on Computer Vision III