Attribute Artifacts Removal for Geometry-Based Point Cloud Compression

Sheng, Xihua; Li, Li; Liu, Dong; Xiong, Zhiwei

doi:10.1109/tip.2022.3170722

Cited by 26 publications

(17 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work thus focuses on the compression artifact reduction (CAR) of G-PCC coded point cloud attribute (PCA). Similar to existing works [2], [15], [16], we assume the Grey cubes stand for positively-occupied voxels which are converted from the raw points by voxelizing the input point cloud [2]. Whether a voxel is occupied is nondeterministic and highly content-dependent because of the dynamic, sparse, and unstructured distribution of points in a point cloud.…”

Section: A Background and Motivationmentioning

confidence: 99%

“…1), which further complicates the characterization of attribute variations from spatial neighbors. Although devising an extremely large-scale network might be capable of learning such spatial variations, the complexity is accordingly unbearable for practical applications [16].…”

Section: A Background and Motivationmentioning

confidence: 99%

“…The main contributions of this paper are summarized below: Relative to state-of-the-art MS-GAT [16] which is a postprocessing solution for artifact removal, our CARNet provides 12.95% BD-Rate gains and costs much less runtime (about 30× speedup). • The efficiency of the CARNet comes from the effective characterization of neighborhood variations for the derivation of the most-probable sample offsets, which are then linearly weighted to produce the best additive offset for compression distortion compensation.…”

Section: Contributionmentioning

confidence: 99%

“…It is also worth pointing out that for fair comparisons with the MS-GAT [16], our CARNet is refined using the same training samples provided by the MS-GAT. For both the MS-GAT and the proposed CARNet, we assume the G-PCC as the compression backbone and keep the same G-PCC codec configuration for comparison.…”

Section: A Experimental Settingsmentioning

confidence: 99%

“…Compared with the MS-GAT [16]. We also compare our CARNet with the MS-GAT [16] -a post-processing method for G-PCC compressed attribute artifacts removal with stateof-the-art performance.…”

Section: A Experimental Settingsmentioning

confidence: 99%

See 4 more Smart Citations

CARNet:Compression Artifact Reduction for Point Cloud Attribute

Ding¹,

Zhang²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

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 G-PCC, where those linear weighting coefficients are encapsulated into the bitstream with negligible bit rate overhead. Experimental results demonstrate significant improvement over the latest G-PCC both subjectively and objectively. For example, our method offers 21.96% YUV BD-Rate (Bjøntegaard Delta Rate) reduction against the G-PCC across various commonly-used test point clouds. Compared with a recent work showing state-of-the-art performance, our work not only gains 12.95% YUV BD-Rate but also provides 30× processing speedup.

show abstract

Section: A Background and Motivationmentioning

confidence: 99%

Section: A Background and Motivationmentioning

confidence: 99%

Section: Contributionmentioning

confidence: 99%

Section: A Experimental Settingsmentioning

confidence: 99%

“…Compared with the MS-GAT [16]. We also compare our CARNet with the MS-GAT [16] -a post-processing method for G-PCC compressed attribute artifacts removal with stateof-the-art performance.…”

Section: A Experimental Settingsmentioning

confidence: 99%

See 3 more Smart Citations