Decoupled Sparse Priors Guided Diffusion Compression Model for Point Clouds

2024-11-21

arXiv.org

AI Summary

Existing point cloud lossy compression methods suffer from degraded reconstruction quality at high compression ratios, primarily due to ineffective modeling of inherent structural redundancy in latent representations. To address this, we propose a disentangled sparse prior-guided diffusion compression model. Our method introduces a dual-density data flow that separates reconstruction-oriented latent points from storage-efficient sparse priors. We further design novel intra- and inter-point hierarchical sparse priors, dynamically conditioned into a progressive-attention diffusion denoiser. Additionally, local distribution modeling is integrated to enhance arithmetic coding efficiency. The framework employs a dual-encoder architecture, conditional diffusion modeling, and hierarchical prior encoding. Evaluated on ShapeNet, 8iVFB, and Owlii benchmarks, our approach achieves state-of-the-art rate-distortion performance—particularly excelling at high compression ratios with significantly improved geometric fidelity and fine-detail recovery.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Data Mining & Knowledge Management: Data Compression
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Lossy compression methods rely on an autoencoder to transform a point cloud into latent points for storage, leaving the inherent redundancy of latent representations unexplored. To reduce redundancy in latent points, we propose a sparse priors guided method that achieves high reconstruction quality, especially at high compression ratios. This is accomplished by a dual-density scheme separately processing the latent points (intended for reconstruction) and the decoupled sparse priors (intended for storage). Our approach features an efficient dual-density data flow that relaxes size constraints on latent points, and hybridizes a progressive conditional diffusion model to encapsulate essential details for reconstruction within the conditions, which are decoupled hierarchically to intra-point and inter-point priors. Specifically, our method encodes the original point cloud into latent points and decoupled sparse priors through separate encoders. Latent points serve as intermediates, while sparse priors act as adaptive conditions. We then employ a progressive attention-based conditional denoiser to generate latent points conditioned on the decoupled priors, allowing the denoiser to dynamically attend to geometric and semantic cues from the priors at each encoding and decoding layer. Additionally, we integrate the local distribution into the arithmetic encoder and decoder to enhance local context modeling of the sparse points. The original point cloud is reconstructed through a point decoder. Compared to state-of-the-art, our method obtains superior rate-distortion trade-off, evidenced by extensive evaluations on the ShapeNet dataset and standard test datasets from MPEG group including 8iVFB, and Owlii.

Problem

• Reducing redundancy in point cloud latent representations for compression
• Improving reconstruction quality at high compression ratios using sparse priors
• Enhancing rate-distortion trade-off through decoupled hierarchical priors

Innovation

• Decoupled sparse priors guide latent compression
• Progressive conditional diffusion model enhances reconstruction
• Dual-density scheme separates storage and processing flows