Recently, 3D Gaussian splatting (3D-GS) has gained popularity in novel-view
scene synthesis. It addresses the challenges of lengthy training times and slow
rendering speeds associated with Neural Radiance Fields (NeRFs). Through rapid,
differentiable rasterization of 3D Gaussians, 3D-GS achieves real-time
rendering and accelerated training. They, however, demand substantial memory
resources for both training and storage, as they require millions of Gaussians
in their point cloud representation for each scene. We present a technique
utilizing quantized embeddings to significantly reduce memory storage
requirements and a coarse-to-fine training strategy for a faster and more
stable optimization of the Gaussian point clouds. Our approach results in scene
representations with fewer Gaussians and quantized representations, leading to
faster training times and rendering speeds for real-time rendering of high
resolution scenes. We reduce memory by more than an order of magnitude all
while maintaining the reconstruction quality. We validate the effectiveness of
our approach on a variety of datasets and scenes preserving the visual quality
while consuming 10-20x less memory and faster training/inference speed. Project
page and code is available this https URL

使用量化嵌入技术和粗到精的训练策略，大幅降低内存存储需求，实现了高分辨率场景的实时渲染和更快更稳定的高斯点云优化，减少了记忆存储量并保持重建质量，验证表明效果显著。

高效加速的轻量级编码的三维高斯模型

EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS

Recently, many works have focused on the characterization of non-linear
dimensionality reduction methods obtained by quantizing linear embeddings,
e.g., to reach fast processing time, efficient data compression procedures,
novel geometry-preserving embeddings or to estimate the information/bits stored
in this reduced data representation. In this work, we prove that many linear
maps known to respect the restricted isometry property (RIP) can induce a
quantized random embedding with controllable multiplicative and additive
distortions with respect to the pairwise distances of the data points beings
considered. In other words, linear matrices having fast matrix-vector
multiplication algorithms (e.g., based on partial Fourier ensembles or on the
adjacency matrix of unbalanced expanders) can be readily used in the definition
of fast quantized embeddings with small distortions. This implication is made
possible by applying right after the linear map an additive and random "dither"
that stabilizes the impact of the uniform scalar quantization operator applied
afterwards. For different categories of RIP matrices, i.e., for different
linear embeddings of a metric space $(\mathcal K \subset \mathbb R^n, \ell_q)$
in $(\mathbb R^m, \ell_p)$ with $p,q \geq 1$, we derive upper bounds on the
additive distortion induced by quantization, showing that it decays either when
the embedding dimension $m$ increases or when the distance of a pair of
embedded vectors in $\mathcal K$ decreases. Finally, we develop a novel
"bi-dithered" quantization scheme, which allows for a reduced distortion that
decreases when the embedding dimension grows and independently of the
considered pair of vectors.

该文研究了如何对线性嵌入进行量化，以实现快速处理时间，高效的数据压缩过程和新颖的保几何嵌入，证明了许多尊重受限等距性质的线性映射可以诱导出一个定量随机嵌入，并介绍了一种新的 “双矫正” 量化方案。