AI Paper Atlas

Research map / 3D vision / Gaussian splatting

MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation

Shuzhao Xie, Weixiang Zhang, Chen Tang, Yunpeng Bai, Rongwei Lu, Shjia Ge, Zhi Wang

ECCV 2024 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 37 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add finetuning after compression (ablation)MesonGS · Synthetic-NeRFPSNR (dB): 29.37 -> 31.75Improved
add finetuning after compression (ablation)MesonGS · Mip-NeRF 360PSNR (dB): 27.20 -> 27.45Improved
replace rotation quaternions with Euler angles (ablation)MesonGS · Synthetic-NeRFPSNR (dB): 30.44 -> 30.44No clear effect
use Euler angles instead of covariance-based replacement (ablation)MesonGS · Positive-definite covariance after quantizationfraction positive definite: ~50% -> 92%Improved
use block quantization instead of per-channel quantization (ablation)MesonGS · Mip-NeRF 360 (tau=50%)PSNR (dB): 25.35 -> 27.20Improved
use block quantization instead of per-channel quantization (ablation)MesonGS · Synthetic-NeRF (tau=66%)PSNR (dB): 29.47 -> 29.60Improved
add view-dependent importance I_d to pruning score (ablation)MesonGS pruning · Mip-NeRF 360PSNR: 27.01 -> 27.52Improved
add view-dependent importance I_d to pruning score (ablation)MesonGS pruning · Synthetic-NeRFPSNR: 30.39 -> 30.52Improved
apply RAHT to scale vectors at 8-bit quantization (ablation)MesonGS · Mip-NeRF 360 / Synthetic-NeRFrendering qualityHurt
prune 33% instead of 66% of Gaussians at 8-bit quantization (ablation)MesonGS · Mip-NeRF 360 (8-bit)rendering qualityHurt
prune Gaussians (66%) before compression (ablation)MesonGS · Mip-NeRF 360size (MB): 641.73 -> 265.94Improved
add vector quantization of 1+D SH coefficients (ablation)MesonGS · Mip-NeRF 360size (MB): 255.61 -> 79.35Improved

Later papers that compared with this method

3 later accepted papers report MesonGS as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy