用空间预测压缩3D高斯点云，节省24%码率
Enhancing 3D Gaussian Splatting Compression via Spatial Condition-based Prediction
- 基于网格信息预测高斯分布，残差补偿还原细节
- 引入实例感知超先验模型，进一步压缩残差数据
- 适合需要高效传输3D场景的实时渲染应用
最近，3D高斯点云（3DGS）因其出色的实时渲染性能在新视角合成（NVS）领域广受关注。然而，原始3DGS的存储与传输成本高昂（单个场景可达数百兆甚至千兆字节），限制了其广泛应用。受视频压缩中预测技术的启发，本文将预测机制引入基于锚点的高斯表示，以有效降低码率。具体地，提出一种基于空间条件的预测模块，利用网格捕获的场景信息进行预测，并设计残差补偿策略以学习缺失的细粒度信息。此外，为更高效压缩残差，提出一种实例感知超先验，构建结构感知且实例感知的熵模型。大量实验验证了所提压缩框架及各组件的有效性，相较于当前最优压缩方法，仍实现24.42%的码率降低。代码即将开源！
原文摘要 · Abstract (English)
Recently, 3D Gaussian Spatting (3DGS) has gained widespread attention in Novel View Synthesis (NVS) due to the remarkable real-time rendering performance. However, the substantial cost of storage and transmission of vanilla 3DGS hinders its further application (hundreds of megabytes or even gigabytes for a single scene). Motivated by the achievements of prediction in video compression, we introduce the prediction technique into the anchor-based Gaussian representation to effectively reduce the bit rate. Specifically, we propose a spatial condition-based prediction module to utilize the grid-captured scene information for prediction, with a residual compensation strategy designed to learn the missing fine-grained information. Besides, to further compress the residual, we propose an instance-aware hyper prior, developing a structure-aware and instance-aware entropy model. Extensive experiments demonstrate the effectiveness of our prediction-based compression framework and each technical component. Even compared with SOTA compression method, our framework still achieves a bit rate savings of 24.42 percent. Code is to be released!
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。