Survey on Deep Learning-Based Point Cloud Compression

Quach, Maurice; Pang, Jiahao; Tian, Dong; Valenzise, Giuseppe; Dufaux, Frédéric

doi:10.3389/frsip.2022.846972

Cited by 32 publications

(10 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Static PCGC. Recently, major endeavors have been paid to study the compression of a static PCG [6], a.k.a. Static PCGC, yielding voxel-based [16], [17], point-based [18], octree-based [19], and sparse tensor-based approaches [7], [2], [1].…”

Section: Related Workmentioning

confidence: 99%

“…Dynamic point clouds are of great importance for applications like holographic communication, autonomous machinery, etc., for which the efficient compression of dynamic Point Cloud Geometry (PCG) plays a vital role in service provisioning. In addition to rules-based Point Cloud Geometry Compression (PCGC) technologies standardized by the ISO/IEC MPEG (Moving Picture Experts Group), e.g., Video-based PCC (V-PCC) and Geometry-based PCC (G-PCC) [3], [4], [5], learning-based PCGC methods have been extensively investigated in the past few years, greatly improving the performance with very encouraging prospects [6]. Among those learningbased solutions, multiscale sparse representation (MSR) [2], [1], [7], [8] has improved the performance unprecedentedly by effectively exploiting cross-scale and same-scale correlations in the same frame of a static PCG for compact representation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Point Cloud Geometry Compression Using Multiscale Inter Conditional Coding

Wang¹,

Ding²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

This work extends the Multiscale Sparse Representation (MSR) framework developed for static Point Cloud Geometry Compression (PCGC) to support the dynamic PCGC through the use of multiscale inter conditional coding. To this end, the reconstruction of the preceding Point Cloud Geometry (PCG) frame is progressively downscaled to generate multiscale temporal priors which are then scale-wise transferred and integrated with lower-scale spatial priors from the same frame to form the contextual information to improve occupancy probability approximation when processing the current PCG frame from one scale to another. Following the Common Test Conditions (CTC) defined in the standardization committee, the proposed method presents State-Of-The-Art (SOTA) compression performance, yielding 78% lossy BD-Rate gain to the latest standard-compliant V-PCC and 45% lossless bitrate reduction to the latest G-PCC. Even for recently-emerged learning-based solutions, our method still shows significant performance gains.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Dynamic Point Cloud Geometry Compression Using Multiscale Inter Conditional Coding

Wang¹,

Ding²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Instead of applying handcrafted rules, data-driven learning is applied to derive (non-linear) transforms and context models directly for PCA compression. Among them, end-to-end supervised learning is the most straightforward solution [26]. Sheng et al [27] designed a point-based lossy attribute autoencoder, where stacked multi-layer perceptrons (MLPs) were used to extract spatial correlations across points and transform the input attribute into high-dimensional features for entropy coding.…”

Section: A Point Cloud Attributes Compressionmentioning

confidence: 99%

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

“…Nowadays, point clouds have been massively used in networked applications including Augmented and Virtual Reality, Autonomous Machinery, etc., making the desire for efficient Point Cloud Compression (PCC) more and more indispensable. In addition to those rules-based PCC solutions, such as Geometry-based PCC (G-PCC) or Video-based PCC (V-PCC) standardized under the ISO/IEC MPEG committee [1], learning-based PCC approaches have attracted worldwide attention and demonstrated noticeable compression gains [2] in Point Cloud Geometry Compression (PCGC). Among them, our earlier multiscale sparse representation-based PCGC has reported state-of-the-art performance [3,4] on a variety of point clouds (e.g., dense object and sparse LiDAR data).…”

Section: Introductionmentioning

confidence: 99%

Lossless Point Cloud Attribute Compression Using Cross-scale, Cross-group, and Cross-color Prediction

Wang¹,

Ding²,

Ma³

2023

Preprint

View full text Add to dashboard Cite

This work extends the multiscale structure originally developed for point cloud geometry compression to point cloud attribute compression. To losslessly encode the attribute while maintaining a low bitrate, accurate probability prediction is critical. With this aim, we extensively exploit cross-scale, cross-group, and cross-color correlations of point cloud attribute to ensure accurate probability estimation and thus high coding efficiency. Specifically, we first generate multiscale attribute tensors through average pooling, by which, for any two consecutive scales, the decoded lower-scale attribute can be used to estimate the attribute probability in the current scale in one shot. Additionally, in each scale, we perform the probability estimation group-wisely following a predefined grouping pattern. In this way, both cross-scale and (same-scale) cross-group correlations are exploited jointly. Furthermore, cross-color redundancy is removed by allowing inter-color processing for YCoCg/RGB alike multi-channel attributes. The proposed method not only demonstrates state-of-the-art compression efficiency with significant performance gains over the latest G-PCC on various contents but also sustains low complexity with affordable encoding and decoding runtime.

show abstract

Survey on Deep Learning-Based Point Cloud Compression

Cited by 32 publications

References 87 publications

Dynamic Point Cloud Geometry Compression Using Multiscale Inter Conditional Coding

Dynamic Point Cloud Geometry Compression Using Multiscale Inter Conditional Coding

CARNet:Compression Artifact Reduction for Point Cloud Attribute

Lossless Point Cloud Attribute Compression Using Cross-scale, Cross-group, and Cross-color Prediction

Contact Info

Product

Resources

About