REVIEW 9 cited by
CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
3D Gaussian Splatting (3DGS) is a new method for modeling and rendering 3D radiance fields that achieves much faster learning and rendering time compared to SOTA NeRF methods. However, it comes with a drawback in the much larger storage demand compared to NeRF methods since it needs to store the parameters for several 3D Gaussians. We notice that many Gaussians may share similar parameters, so we introduce a simple vector quantization method based on K-means to quantize the Gaussian parameters while optimizing them. Then, we store the small codebook along with the index of the code for each Gaussian. We compress the indices further by sorting them and using a method similar to run-length encoding. Moreover, we use a simple regularizer to encourage zero opacity (invisible Gaussians) to reduce the storage and rendering time by a large factor through reducing the number of Gaussians. We do extensive experiments on standard benchmarks as well as an existing 3D dataset that is an order of magnitude larger than the standard benchmarks used in this field. We show that our simple yet effective method can reduce the storage cost for 3DGS by 40 to 50x and rendering time by 2 to 3x with a very small drop in the quality of rendered images.
Forward citations
Cited by 9 Pith papers
-
AdaptiveSplat:Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction
Texture-aware SuperCluster pruning plus an adaptive Gaussian head lets feed-forward 3DGS models hit a user budget β while outperforming post-hoc pruners on RE10K, ACID, DL3DV and DTU.
-
Signal Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstruction
SIG synchronizes training-image resolution and Gaussian densification to measured scene bandwidth, plus sphere constraints on primitives, delivering better PSNR and 1.4–1.5× per-block speedups on large outdoor scenes.
-
CF3: Compact and Fast 3D Feature Fields
CF3 builds a compact 3D feature field from a pre-trained 3DGS by feature lifting, per-Gaussian autoencoding, and adaptive sparsification, matching baseline segmentation quality with roughly 5% of the Gaussians.
-
NeRF Is a Valuable Assistant for 3D Gaussian Splatting
NeRF-GS jointly optimizes a NeRF and a 3D Gaussian Splatting model in one scene, using shared features, residual corrections, and mutual loss constraints to beat both standalone methods.
-
FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting
FlexGaussian is a training-free pipeline that prunes and quantizes 3D Gaussian Splatting scenes, achieving up to 96.4% compression with less than 1 dB PSNR drop.
-
FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting
A single 3DGS model with a learned Gaussian selector and transform field renders at any requested compression ratio without fine-tuning.
-
Adaptive Voxelization for Transform coding of 3D Gaussian splatting data
An adaptive voxelization scheme tailored to 3D Gaussian splatting, combined with attribute initialization for fine-tuning, enables hybrid transform coding that outperforms post-training codecs on two benchmark scenes.
-
Enhancing LLM Training via Spectral Clipping
SPECTRA improves LLM pretraining via post-clipping of update spectral norms and optional pre-clipping of gradient spikes, framed as Composite Frank-Wolfe regularization.
-
Perceive-Sample-Compress: Towards Real-Time 3D Gaussian Splatting
A three-stage perceive-sample-compress framework for 3D Gaussian Splatting improves rendering fidelity and storage efficiency across small and large scenes.
Discussion (0). Sign in to comment.