LightGaussian：实现15倍压缩与200+ FPS的无界3D高斯压缩
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
AI总结：
LightGaussian通过剪枝、知识蒸馏和向量量化将3D高斯转换为紧凑格式，在保持视觉质量的同时实现15倍压缩并提升渲染速度，有效解决了3D场景的存储和效率问题。
摘要：
近期基于点技术的实时神经渲染进展促进了3D表示的广泛应用。然而，像3D Gaussian Splatting这样的基础方法带来了巨大的存储开销，因为Structure-from-Motion (SfM) 点可以增长到数百万个，通常需要GB级的磁盘空间来存储单个无界场景。这种增长带来了可扩展性挑战并阻碍了splatting效率。为了解决这个问题，我们引入了LightGaussian，一种将3D高斯转换为更紧凑格式的方法。受Network Pruning启发，LightGaussian识别出对场景重建具有最小全局重要性的高斯，并应用剪枝和恢复过程以减少冗余，同时保持视觉质量。知识蒸馏和伪视图增强随后将球谐系数转移到较低阶数，产生紧凑的表示。基于每个高斯全局重要性的Gaussian Vector Quantization进一步降低了位宽，且精度损失极小。LightGaussian实现了平均15倍的压缩率，同时在3D-GS框架内将FPS从144提升至237，在Mip-NeRF 360和Tank & Temple数据集上实现了高效的复杂场景表示。所提出的Gaussian剪枝方法也可适应于其他3D表示（如Scaffold-GS），展现出强大的泛化能力。
英文摘要：
Recent advances in real-time neural rendering using point-based techniques have enabled broader adoption of 3D representations. However, foundational approaches like 3D Gaussian Splatting impose substantial storage overhead, as Structure-from-Motion (SfM) points can grow to millions, often requiring gigabyte-level disk space for a single unbounded scene. This growth presents scalability challenges and hinders splatting efficiency. To address this, we introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies Gaussians with minimal global significance on scene reconstruction, and applies a pruning and recovery process to reduce redundancy while preserving visual quality. Knowledge distillation and pseudo-view augmentation then transfer spherical harmonic coefficients to a lower degree, yielding compact representations. Gaussian Vector Quantization, based on each Gaussian's global significance, further lowers bitwidth with minimal accuracy loss. LightGaussian achieves an average 15x compression rate while boosting FPS from 144 to 237 within the 3D-GS framework, enabling efficient complex scene representation on the Mip-NeRF 360 and Tank & Temple datasets. The proposed Gaussian pruning approach is also adaptable to other 3D representations (e.g., Scaffold-GS), demonstrating strong generalization capabilities.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
