# CARNet:Compression Artifact Reduction for Point Cloud Attribute

arXiv: https://arxiv.org/abs/2209.08276 · HTML: https://mlsanity.com/paper/2209.08276/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 45 references that are in the map.
- First posted on arXiv 17 Sep 2022.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Compression Artifacts Reduction by a Deep Convolutional Network](https://mlsanity.com/paper/1504.06993/) (2015)
- [Multiscale Point Cloud Geometry Compression](https://mlsanity.com/paper/2011.03799/) (2020)
- [Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression](https://mlsanity.com/paper/2111.10633/) (2021)
- [MFQE 2.0: A New Approach for Multi-frame Quality Enhancement on Compressed Video](https://mlsanity.com/paper/1902.09707/) (2019)
- [Density-preserving Deep Point Cloud Compression](https://mlsanity.com/paper/2204.12684/) (2022)
- [Sparse Tensor-based Point Cloud Attribute Compression](https://mlsanity.com/paper/2204.01023/) (2022)
- [3DAC: Learning Attribute Compression for Point Clouds](https://mlsanity.com/paper/2203.09931/) (2022)
- [MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering](https://mlsanity.com/paper/2007.07099/) (2020)
- [Attribute Artifacts Removal for Geometry-based Point Cloud Compression](https://mlsanity.com/paper/2112.00560/) (2021)
- [A CNN-based Prediction-Aware Quality Enhancement Framework for VVC](https://mlsanity.com/paper/2105.05658/) (2021)
- [Residual-Guided In-Loop Filter Using Convolution Neural Network](https://mlsanity.com/paper/1907.12681/) (2019)
- [Combining Progressive Rethinking and Collaborative Learning: A Deep Framework for In-Loop Filtering](https://mlsanity.com/paper/2001.05651/) (2020)

## Built on by (most cited first, 6 of 6)

- [SPAC: Sampling-based Progressive Attribute Compression for Dense Point Clouds](https://mlsanity.com/paper/2409.10293/) (2024)
- [PCE-GAN: A Generative Adversarial Network for Point Cloud Attribute Quality Enhancement based on Optimal Transport](https://mlsanity.com/paper/2503.00047/) (2025)
- [Implicit Neural Compression of Point Clouds](https://mlsanity.com/paper/2412.10433/) (2024)
- [Generalized Gaussian Entropy Model for Point Cloud Attribute Compression with Dynamic Likelihood Intervals](https://mlsanity.com/paper/2506.09510/) (2025)
- [UGAE: Unified Geometry and Attribute Enhancement for G-PCC Compressed Point Clouds](https://mlsanity.com/paper/2510.23009/) (2025)
- [DUGAE: Unified Geometry and Attribute Enhancement via Spatiotemporal Correlations for G-PCC Compressed Dynamic Point Clouds](https://mlsanity.com/paper/2603.26183/) (2026)

## Abstract (arXiv)

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.