Wan Fang, Zhang Jianhang, Li Tianyu, Lei Guangbo, Xu Li, Ye Zhiwei
Hubei University of Technology, School of Computer Science, Wuhan, Hubei, 430068, China.
Peking University College of Engineering, Beijing, Beijing, 100091, China.
Neural Netw. 2026 Feb;194:108134. doi: 10.1016/j.neunet.2025.108134. Epub 2025 Sep 20.
Neural Radiance Fields (NeRF) have demonstrated remarkable performance in the field of novel view synthesis (NVS). However, their high computational cost limits practical applicability. The 3D Gaussian Splatting (3DGS) method offers a significant improvement in rendering efficiency, enabling real-time rendering through its explicit representations. Nevertheless, its substantial storage requirements pose challenges for complex scenes and resource-constrained devices. Existing methods aim to achieve storage compression through redundant point pruning, spherical harmonics adjustment, and vector quantization. However, point pruning methods often compromise geometric details in complex structures, while vector quantization approaches fail to capture feature relationships effectively, resulting in texture degradation and geometric boundary blurring. Although anchor point representations partially address storage concerns, their sparse representation limits compression efficiency. These limitations become particularly evident in scenes with intricate textures and complex lighting conditions. To ensure optimal compression ratios while maintaining high fidelity in Gaussian scenarios, this paper proposes an Attention-Aware Adaptive Codebook Gaussian Splatting (AAC-GS) method for efficient storage compression. The approach dynamically adjusts the size of the codebook to optimize storage efficiency and incorporates an attention mechanism to capture feature contextual relationships, thereby enhancing reconstruction quality. Additionally, a Generative Adversarial Network (GAN) is employed to mitigate quantization losses, achieving a balance between compression rate and visual fidelity. Experimental results demonstrate that AAC-GS achieves an average compression ratio of approximately 40× while maintaining high reconstruction quality, showcasing its potential for multi-scene applications.
神经辐射场（NeRF）在新视图合成（NVS）领域展现出了卓越的性能。然而，其高昂的计算成本限制了实际应用。3D高斯点云（3DGS）方法在渲染效率方面有显著提升，通过其显式表示实现了实时渲染。尽管如此，其巨大的存储需求给复杂场景和资源受限设备带来了挑战。现有方法旨在通过冗余点裁剪、球谐函数调整和矢量量化来实现存储压缩。然而，点裁剪方法往往会在复杂结构中牺牲几何细节，而矢量量化方法无法有效捕捉特征关系，导致纹理退化和几何边界模糊。尽管锚点表示部分解决了存储问题，但其稀疏表示限制了压缩效率。这些限制在具有复杂纹理和复杂光照条件的场景中尤为明显。为了在高斯场景中确保最佳压缩比并保持高保真度，本文提出了一种注意力感知自适应码本高斯点云（AAC-GS）方法，用于高效存储压缩。该方法动态调整码本大小以优化存储效率，并引入注意力机制来捕捉特征上下文关系，从而提高重建质量。此外，采用生成对抗网络（GAN）来减轻量化损失，在压缩率和视觉保真度之间取得平衡。实验结果表明，AAC-GS在保持高重建质量的同时实现了约40倍的平均压缩比，展示了其在多场景应用中的潜力。
