AI Paper Atlas

Research map / 3D vision / Gaussian splatting

SAGS: Structure-Aware 3D Gaussian Splatting

Evangelos Ververas, Rolandos Alexandros Potamias, Jifei Song, Jiankang Deng, Stefanos Zafeiriou

ECCV 2024 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 20 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 curvature-aware densification (ablation)SAGS · Deep BlendingPSNR: 29.87 -> 30.47Improved
add GNN aggregation instead of MLP (ablation)SAGS · Deep BlendingPSNR: 29.94 -> 30.47Improved
add GNN aggregation instead of MLP (ablation)SAGS · Tanks&TemplesPSNR: 24.19 -> 24.88Improved
add curvature-aware densification (ablation)SAGS · Tanks&TemplesPSNR: 23.97 -> 24.88Improved
add positional encoding of point positions (ablation)SAGS · Deep BlendingPSNR: 30.21 -> 30.47Improved
add global feature g (ablation)SAGS · Tanks&TemplesPSNR: 24.42 -> 24.88Improved
add view-dependent positions to appearance attributes (ablation)SAGS · Deep BlendingPSNR: 30.07 -> 30.47Improved
structure-aware GNN model vs structure-agnostic Scaffold-GSSAGS · Mip-NeRF360PSNR: 28.84 -> 29.65Improved
use lightweight midpoint-interpolation model (SAGS-Lite) instead of full SAGSSAGS · Deep Blendingmodel size (MB): 58 -> 28Improved
use SAGS-Lite instead of full SAGSSAGS · Deep BlendingPSNR: 30.47 -> 29.07Hurt
SAGS vs Scaffold-GS storageSAGS · Mip-NeRF360model size (MB): 252 -> 135Improved

Later papers that compared with this method

2 later accepted papers report SAGS as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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