CARNet:Compression Artifact Reduction for Point Cloud Attribute

TL;DR

This paper introduces CARNet, a learning-based adaptive filter for point cloud attribute compression, which effectively reduces artifacts by modeling local variations and adaptively combining multiple distortion approximations, leading to improved compression quality.

Contribution

The paper presents a novel neural network-based in-loop filtering method that adaptively reduces compression artifacts in point cloud attributes with minimal bitstream overhead.

Findings

Significant artifact reduction demonstrated both subjectively and objectively.

Effective modeling of local neighborhood variations using sparse convolutions.

Adaptive combination of multiple distortion approximations improves reconstruction quality.

Abstract

A learning-based adaptive loop filter is developed for the Geometry-based Point Cloud Compression (G-PCC) standard to reduce attribute compression artifacts. The proposed method first generates multiple Most-Probable Sample Offsets (MPSOs) as potential compression distortion approximations, and then linearly weights them for artifact mitigation. As such, we drive the filtered reconstruction as close to the uncompressed PCA as possible. To this end, we devise a Compression Artifact Reduction Network (CARNet) which consists of two consecutive processing phases: MPSOs derivation and MPSOs combination. The MPSOs derivation uses a two-stream network to model local neighborhood variations from direct spatial embedding and frequency-dependent embedding, where sparse convolutions are utilized to best aggregate information from sparsely and irregularly distributed points. The MPSOs combination is guided by the least square error metric to derive weighting coefficients on the fly to further capture content dynamics of input PCAs. The CARNet is implemented as an in-loop filtering tool of the GPCC, where those linear weighting coefficients are encapsulated into the bitstream with negligible bit rate overhead. Experimental results demonstrate significant improvement over the latest GPCC both subjectively and objectively.