AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Pixel-GS Density Control with Pixel-aware Gradient for 3D Gaussian Splatting

Zheng Zhang, Wenbo Hu, Yixing Lao, Tong He, Hengshuang Zhao

ECCV 2024 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 130 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
weight per-view gradient by covered pixel count (pixel-aware gradient) in the growth condition (ablation)3DGS* · Mip-NeRF 360LPIPS: 0.202 -> 0.176Improved
add pixel-aware gradient alone (ablation)3DGS* · Tanks & TemplesPSNR: 24.23 -> 21.80Hurt
add scaled gradient field (distance-based scaling) alone (ablation)3DGS* · Tanks & TemplesPSNR: 24.23 -> 24.34Improved
add scaled gradient field alone (ablation)3DGS* · Mip-NeRF 360LPIPS: 0.202 -> 0.202No clear effect
add scaled gradient field to pixel-aware gradient (ablation)Pixel-GS · Tanks & TemplesPSNR: 21.80 -> 24.38Improved
lower growth threshold of 3DGS* from 2e-4 to 1.28e-4 instead of using pixel-aware gradient (ablation)3DGS* · Mip-NeRF 360LPIPS: 0.202 -> 0.181 (Pixel-GS 0.176)Mixed
lower growth threshold of 3DGS* to 1e-4 (ablation)3DGS* · Tanks & TemplesPSNR: 24.19 -> 23.86Hurt
use Pixel-GS instead of 3DGS*3DGS* · Mip-NeRF 360FPS: 126 -> 89Hurt
drop up to 99% of initial SfM pointsPixel-GS vs 3DGS · Mip-NeRF 360LPIPSImproved

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