AI Paper Atlas

Research map / 3D vision / Gaussian splatting

RAP: Fast Feedforward Rendering-Free Attribute-Guided Primitive Importance Score Prediction for Efficient 3D Gaussian Splatting Processing

Kaifa Yang, Qi Yang, Yiling Xu, Zhu Li

CVPR 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 3 citations (OpenAlex)

Read the paper

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
use RAP scores instead of opacity thresholding for pruning3DGS · Mip-NeRF360 OutdoorBD-Rate (%): -42.63 vs opacity baselineImproved
use PUP-3DGS scores instead of opacity on Tanks&Temples3DGS · Tanks&TemplesBD-Rate (%): +7.06Hurt
use RAP scores in pruning-in-the-loop training3DGS · Mip-NeRF360 OutdoorPSNR: 24.688 -> 24.709Improved
use RAP scores in pruning-in-the-loop training3DGS · Mip-NeRF360 IndoorPSNR: 31.076 -> 30.696Hurt
pre-prune 20% of Gaussians with importance scores before MPEG GSCGSC (G-PCC and video) · MPEG GSC R-DBD-Rate: 15-20% BD-Rate gains for most methodsImproved
add opacity feature (ablation)RAP · post-hoc pruningPSNR: about 1-2 dB drop when removedImproved
add Gaussian scale features (ablation)RAP · post-hoc pruningPSNR: about 0.5-1 dB drop when removedImproved
add local or global normalization (each) (ablation)RAP · post-hoc pruningPSNR: 1.5-2 dB drop when either removedImproved
add pruning-aware loss (ablation)RAP · post-hoc pruningPSNR: about 0.5 dB drop on average when removedImproved
add distribution regularization loss (ablation)RAP · post-hoc pruning, low retentionPSNR: approximately 0.25 dBImproved
add color anisotropy and KNN distance features (ablation)RAP · post-hoc pruningPSNRImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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