AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Compression of 3D Gaussian Splatting with Optimized Feature Planes and Standard Video Codecs

Soonbin Lee, Fangwen Shu, Yago Sanchez, Thomas Schierl, Cornelius Hellge

ICCV 2025 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 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 progressive channel-masking training (ablation)feature-plane 3DGS compression · Mip-NeRF360size (MB): 23.45 -> 22.81Improved
add progressive training (ablation)feature-plane 3DGS compression · Mip-NeRF360PSNR (dB): 27.27 -> 27.40Improved
add entropy loss L_ent on top of L1 (ablation)feature-plane 3DGS compression · Mip-NeRF360size (MB): 22.81 -> 10.68Improved
add entropy loss L_ent on top of L1 (ablation)feature-plane 3DGS compression · Mip-NeRF360PSNR (dB): 27.40 -> 27.31No clear effect
add channel importance bit allocation weights w_c (ablation)feature-plane 3DGS compression · Mip-NeRF360size (MB): 10.68 -> 9.96Improved
add piecewise-projective contraction (ablation)feature-plane 3DGS compression · Mip-NeRF360size (MB): 9.96 -> 9.78Improved
apply the proposed feature-plane method with HM codec (ablation)3DGS compression · Tank & Templessize (MB): 27.9 -> 7.46Improved
apply the proposed method with libx265 codec (ablation)3DGS compression · Tank & Templessize (MB): 29.2 -> 7.79Improved
apply the proposed method with HM codec (ablation)3DGS compression · Tank & TemplesPSNR (dB): 23.71 -> 23.63Hurt
apply the proposed method with libx265 codec (ablation)3DGS compression · Tank & TemplesEnc/Dec time (s): 27.5/0.7 -> 25.3/0.6Improved
raise Q_step from 2^0 to 2^8 (ablation)feature-plane compression · Mip-NeRF360 bonsaifeature plane size (MB): 16.6 -> 8.45Improved
raise Q_step from 2^8 to 2^12 (ablation)feature-plane compression · Mip-NeRF360 bonsaifeature plane size (MB): 8.45 -> 17.8Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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