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

Shanghai Jiao Tong University
CVPR 2026

Abstract

We propose RAP, a fast rendering-free importance prediction method for 3D Gaussian Splatting. RAP leverages intrinsic Gaussian attributes and local neighborhood statistics to directly predict primitive importance using a lightweight MLP, without requiring multi-view rendering analysis. The method generalizes well and can serve as a plug-and-play module for pruning, compression, and transmission tasks, significantly improving efficiency and storage compactness while preserving reconstruction quality.

RAP Training and Inference Framework

The figure below shows the training framework of RAP. During training, RAP learns importance prediction from intrinsic Gaussian attributes and local neighborhood statistics. During evaluation, we directly extract features and feed them into the trained MLP to obtain importance scores, without rendering-based analysis.

RAP training and inference framework

Direct Pruning without Optimization

RD curves on Mip-NeRF360, Deep Blending, and Tanks&Temples. This result corresponds to direct pruning without post-optimization.

RD curve by PSNR on Mip-NeRF360, Deep Blending, and Tanks and Temples

Reconstruction with Pruning

Results of reconstruction with pruning 40% primitives every 1500 iterations.

Iterative pruning with 40 percent removal every 1500 iterations

5% Primitive Retention Visualization

Only 5% primitives are retained. LightGS (visibility-based) tends to preserve central regions that are visible from most views, often causing strong background distortion. PUP (gradient-based) tends to preserve boundaries. RAP provides a more uniform downsampling over the whole scene. Different importance prediction strategies can be selected based on application needs.

GT

Ground truth at selected scene

LightGS

LightGS result at selected scene

PUP

PUP result at selected scene

RAP

RAP result at selected scene

BibTeX

@article{yang2026rap,
  title={RAP: Fast Feedforward Rendering-Free Attribute-Guided Primitive Importance Score Prediction for Efficient 3D Gaussian Splatting Processing},
  author={Kaifa Yang and Qi Yang and Yiling Xu and Zhu Li},
  journal={CVPR},
  year={2026},
  url={https://sekiroyyy.github.io/rap_webpage/}
}