Blind Quality Enhancement for G-PCC Compressed Dynamic Point Clouds

Abstract

Point cloud compression often introduces noticeable reconstruction artifacts, which makes quality enhancement necessary. Existing approaches typically assume prior knowledge of the distortion level and train multiple models with identical architectures, each designed for a specific distortion setting. This significantly limits their practical applicability in scenarios where the distortion level is unknown and computational resources are limited. To overcome these limitations, we propose the first blind quality enhancement (BQE) model for compressed dynamic point clouds. BQE enhances compressed point clouds under unknown distortion levels by exploiting temporal dependencies and jointly modeling feature similarity and differences across multiple distortion levels. It consists of a joint progressive feature extraction branch and an adaptive feature fusion branch. In the joint progressive feature extraction branch, consecutive reconstructed frames are first fed into a recoloring-based motion compensation module to generate temporally aligned virtual reference frames. These frames are then fused by a temporal correlation-guided cross-attention module and processed by a progressive feature extraction module to obtain hierarchical features at different distortion levels. In the adaptive feature fusion branch, the current reconstructed frame is input to a quality estimation module to predict a weighting distribution that guides the adaptive weighted fusion of these hierarchical features. When applied to the latest geometry-based point cloud compression (G-PCC) reference software, i.e., test model category13 version 28, BQE achieved average PSNR improvements of 0.535 dB, 0.403 dB, and 0.453 dB, with BD-rates of -17.4%, -20.5%, and -20.1% for the Luma, Cb, and Cr components, respectively.

Figures (7)

• Figure 1: BQE architecture. The proposed BQE model consists of two branches: a joint progressive feature extraction branch and an adaptive feature fusion branch. Given a reconstructed point cloud sequence $(\hat{\bm{P}}_{t-R}, \ldots, \hat{\bm{P}}_{t}, \ldots, \hat{\bm{P}}_{t+R})$, where $\hat{\bm{P}}_{t}$ is the target frame and the remaining frames are reference frames, the goal of blind attribute quality enhancement is to restore $\hat{\bm{P}}_{t}$ to an enhanced version ${\widetilde{\bm{P}}}_t$ without knowing the distortion level of $\hat{\bm{P}}_{t}$. Note that the target frame is unchanged by RMC, i.e., $\hat{\bm{P}}'_t = \hat{\bm{P}}_t$.
• Figure 2: Structure of the TCCA module. The ordered sequence $(\hat{\bm{P}}'_{t-R},\,\ldots,\,\hat{\bm{P}}'_{t},\,\ldots,\,\hat{\bm{P}}'_{t+R})$ denotes the virtual frames produced by the RMC module. For notational consistency, we use a prime to indicate frames after RMC. In particular, the target frame is unchanged by RMC, i.e., $\hat{\bm{P}}'_{t}=\hat{\bm{P}}_{t}$.
• Figure 3: Architecture of the NA module.
• Figure 4: Rate-PSNR curves before and after integrating BQE into G-PCC.
• Figure 5: Rate-PSNR curves before and after integrating BQE into GeSTMv8.