AI Paper Atlas

Research map / 3D vision / Gaussian splatting

REFINE: Super-efficient Pruning for 3D Gaussian Splatting via Rendering-Free Primitive Importance

Zhang Chen, Shuai Wan, Mengting Yu, Fuzheng Yang, Junhui Hou

ECCV 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting

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 rendering-free Hessian importance (REFINE) instead of parameter heuristics (LightGaussian)3DGS pruning · MipNeRF360 (ratio 0.5)PSNR: 22.21 -> 26.61Improved
use REFINE instead of render-aware PUP at ratio 0.53DGS pruning · MipNeRF360 (ratio 0.5)PSNR: 26.07 -> 26.61Improved
use REFINE instead of PUP at ratio 0.53DGS pruning · Tanks&Temples (ratio 0.5)PSNR: 23.18 -> 22.97Hurt
use REFINE instead of PUP at extreme ratio 0.73DGS pruning · DeepBlending (ratio 0.7)PSNR: 29.14 -> 27.93Hurt
use REFINE instead of PUP at ratio 0.73DGS pruning · MipNeRF360 (ratio 0.7)PSNR: 25.12 -> 24.43Hurt
use REFINE instead of PUP for pruning cost3DGS pruning · MipNeRF360 (ratio 0.7)GFLOPs: 9582.81 -> 3.14Improved
use REFINE instead of PUP for latency3DGS pruning · MipNeRF360 (ratio 0.7)Time (s): 38.15 -> 2.55Improved
add view-dependent visibility term (ablation)REFINE · Mip360 subset (ratio 0.5)PSNR: 27.74 -> 28.35Improved
add geometric projection term (ablation)REFINE · Mip360 subset (ratio 0.5)PSNR: 27.24 -> 28.35Improved
use content-adaptive lambda instead of equal lambda (ablation)REFINE · Mip360 subset (ratio 0.5)PSNR: 27.82 -> 28.35Improved
fine-tune after pruning, REFINE vs PUP at ratio 0.73DGS pruning · Mip360 kitchen (fine-tuned, ratio 0.7)PSNR: 29.11 -> 30.55 PSNR; LPIPS 0.137 -> 0.152Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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