Video-Based Point Cloud Compression Artifact Removal

Photo-realistic point cloud capture and transmission are the fundamental enablers for immersive visual communication. The coding process of dynamic clouds, especially video-based compression (V-PCC) developed by MPEG standardization group, is now delivering state-of-the-art performance in efficiency. V-PCC based on projection patches to 2D planes encoding sequence as texture geometry patch sequences. However, resulting quantization errors from can introduce artifacts, which be very unpleasant quality experience (QoE). In this work, we a novel out-of-the-loop artifact removal solution that significantly improve reconstruction without additional bandwidth cost. Our framework consists sampling scheme, an network, aggregation scheme. scheme employs cube-based neighborhood extraction divide into patches. network then processes these obtain artifact-removed merged together using final cloud. We employ 3D deep convolutional feature learning jointly recovers both direction noise level exploiting prior. simulation results demonstrate proposed method highly effective considerably reconstructed