DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization

2025-01-19

AI Summary

To address semantic ambiguity in point cloud completion caused by multi-view sampling variability, this paper proposes a dual-codebook vector quantization (VQ) encoder-decoder architecture. The method introduces co-optimized encoder and decoder codebooks, coupled with a cross-level feature interaction mechanism: shallow layers capture local geometric patterns, while deep layers model global structure, enabling multi-granularity semantic alignment. The model is end-to-end trainable and effectively unifies semantic representations across diverse point cloud samplings of the same object. Evaluated on PCN, ShapeNet_Part, and ShapeNet34, it achieves state-of-the-art performance, with significant improvements in Chamfer Distance (CD) and F-Score. Notably, it demonstrates superior robustness under sparse and irregular input conditions.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Point cloud completion aims to reconstruct complete 3D shapes from partial 3D point clouds. With advancements in deep learning techniques, various methods for point cloud completion have been developed. Despite achieving encouraging results, a significant issue remains: these methods often overlook the variability in point clouds sampled from a single 3D object surface. This variability can lead to ambiguity and hinder the achievement of more precise completion results. Therefore, in this study, we introduce a novel point cloud completion network, namely Dual-Codebook Point Completion Network (DC-PCN), following an encder-decoder pipeline. The primary objective of DC-PCN is to formulate a singular representation of sampled point clouds originating from the same 3D surface. DC-PCN introduces a dual-codebook design to quantize point-cloud representations from a multilevel perspective. It consists of an encoder-codebook and a decoder-codebook, designed to capture distinct point cloud patterns at shallow and deep levels. Additionally, to enhance the information flow between these two codebooks, we devise an information exchange mechanism. This approach ensures that crucial features and patterns from both shallow and deep levels are effectively utilized for completion. Extensive experiments on the PCN, ShapeNet_Part, and ShapeNet34 datasets demonstrate the state-of-the-art performance of our method.

Problem

• Point Cloud Completion
• 3D Reconstruction
• Complex Shape

Innovation

• DC-PCN
• Dual Codebook Mechanism
• Information Exchange Mechanism