LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:RQBLXCBErecord.jsonopen to challenge →
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 10 Pith papers
-
Learning Efficient 4D Gaussian Representations from Monocular Videos with Flow Splatting
Flow Splatting extends 4D Gaussian volumes with time-varying means and covariances, approximates a velocity field, and splats it to render optical flow for supervising dynamic reconstruction from monocular video.
-
Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios
RefineSplat applies entropy-aware adaptive masking and density control to 3DGS to remove color- or semantically ambiguous distractors, validated on a new 18-scene Ambiguous wild dataset with claimed SOTA results.
-
EvoGS: Constructing Continuous-Layered Gaussian Splatting with Evolution Tree for Scalable 3D Streaming
EvoGS proposes the first continuous-layering 3D Gaussian Splatting representation via an Evolution Tree to reduce splat redundancy and transmission costs for scalable streaming.
-
Gaussians on a Diet: High-Quality Memory-Bounded 3D Gaussian Splatting Training
A dynamic training framework for 3D Gaussian Splatting alternates incremental pruning and adaptive growing of primitives to maintain high rendering quality at up to 80% lower peak memory than standard 3DGS.
-
SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction
A feed-forward model regresses accurate Gaussian surfel geometry from sparse views using Nyquist-guided cross-view feature aggregation, achieving 100x speedup over optimization-based 3DGS surface methods on DTU benchmarks.
-
Compact 3D Gaussian Splatting For Dense Visual SLAM
A compact 3D Gaussian Splatting SLAM system reduces Gaussian count and parameter size via masking and a geometry codebook while preserving SOTA reconstruction quality and pose accuracy.
-
Pocket-SLAM: Rendering-Area-Aware Pruning for Memory-Efficient 3DGS-SLAM
Pocket-SLAM introduces rendering-area-aware pruning for 3DGS-SLAM, claiming over 60% memory reduction and 2x FPS gain on EuRoC and KITTI while keeping localization and mapping accuracy.
-
Improving 3D Gaussian Splatting Compression by Scene-Adaptive Lattice Vector Quantization
Scene-adaptive lattice vector quantization improves rate-distortion performance of 3DGS compression over uniform scalar quantization while adding little overhead and supporting multiple bit rates from one trained model.
-
Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields
Turbo-GS accelerates 3D Gaussian Splatting training via dilated rendering of pixel subsets, convergence-aware Gaussian budget allocation, and combined positional-appearance error densification to enable faster 4K fitt...
-
A Survey on 3D Gaussian Splatting
A survey compiling principles, applications, benchmarks, and challenges of 3D Gaussian Splatting for explicit 3D scene representation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.