4DAC: A Learning-Based Attribute Compression Framework for Dynamic Point Clouds
4DAC: Learning Attribute Compression for Dynamic Point Clouds
In this paper, we study the attribute (e.g.,color) compression of dynamic point clouds and present a learning-based framework, termed 4dac.To reduce temporal redundancy within data, we first build the 3d motion estimation and motion compensation modules with deep neuralnetworks.Then, the attribute residuals produced by the motion compensationcomponent are encoded by the region adaptive hierarchical transform into residual coefficients.In addition, we also propose a deep conditional entropy model to estimate the probability distribution of the transformed coefficients, by incorporating temporal context from consecutive point clouds and the motionestimation/compensation modules.Finally, the data stream is losslessly entropycoded with the predicted distribution.Extensive experiments on several public datasets demonstrate the superior compression performance of the proposed approach.
