通过时空关联统一增强动态点云的几何与属性质量。
DUGAE: Unified Geometry and Attribute Enhancement via Spatiotemporal Correlations for G-PCC Compressed Dynamic Point Clouds
- 利用稀疏卷积与运动补偿，融合多帧时空信息进行几何增强。
- 几何增益达11.03 dB，比特率降低93.95%，亮度分量提升4.23 dB。
- 适合高保真动态点云重建，尤其适用于视频压缩场景。
现有点云解码后质量增强方法针对静态数据设计，通常独立处理每帧，无法有效利用点云序列中的时空相关性。本文提出统一几何与属性增强框架DUGAE，显式利用几何与属性在帧间的时空相关性。首先，基于稀疏卷积（SPConv）和特征域几何运动补偿（GMC）的动态几何增强网络（DGE-Net）对齐并聚合时空信息；其次，编码端采用细节感知的k近邻（DA-KNN）重着色模块，将原始属性映射至增强几何，提升映射完整性和属性细节保留；最后，具有专用时序特征提取与特征域属性运动补偿（AMC）的动态属性增强网络（DAE-Net）建模复杂时空相关性以优化属性。在8iVFB v2、Owlii和MVUB数据集上的七个动态点云上，DUGAE显著提升最新G-PCC几何基实体内容测试模型（GeS-TM v10）性能：几何（D1）平均获得11.03 dB BD-PSNR增益与93.95% BD-bitrate降低；亮度分量实现4.23 dB BD-PSNR增益与66.61% BD-bitrate降低。同时提升感知质量（PCQM指标），优于V-PCC。源代码将发布于GitHub。
原文摘要 · Abstract (English)
Existing post-decoding quality enhancement methods for point clouds are designed for static data and typically process each frame independently. As a result, they cannot effectively exploit the spatiotemporal correlations present in point cloud sequences.We propose a unified geometry and attribute enhancement framework (DUGAE) for G-PCC compressed dynamic point clouds that explicitly exploits inter-frame spatiotemporal correlations in both geometry and attributes. First, a dynamic geometry enhancement network (DGE-Net) based on sparse convolution (SPConv) and feature-domain geometry motion compensation (GMC) aligns and aggregates spatiotemporal information. Then, a detail-aware k-nearest neighbors (DA-KNN) recoloring module maps the original attributes onto the enhanced geometry at the encoder side, improving mapping completeness and preserving attribute details. Finally, a dynamic attribute enhancement network (DAE-Net) with dedicated temporal feature extraction and feature-domain attribute motion compensation (AMC) refines attributes by modeling complex spatiotemporal correlations. On seven dynamic point clouds from the 8iVFB v2, Owlii, and MVUB datasets, DUGAE significantly enhanced the performance of the latest G-PCC geometry-based solid content test model (GeS-TM v10). For geometry (D1), it achieved an average BD-PSNR gain of 11.03 dB and a 93.95% BD-bitrate reduction. For the luma component, it achieved a 4.23 dB BD-PSNR gain with a 66.61% BD-bitrate reduction. DUGAE also improved perceptual quality (as measured by PCQM) and outperformed V-PCC. Our source code will be released on GitHub at: https://github.com/yuanhui0325/DUGAE
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。