AI Paper Atlas

Research map / 3D vision / Gaussian splatting

EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS

Sharath Girish, Kamal Gupta, Abhinav Shrivastava

ECCV 2024 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 183 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
quantize color, rotation and opacity attributes with latent decoder (ablation)3D-GS · Train scene (Tanks&Temples)Storage memory: 262MB -> 46MBImproved
quantize color, rotation and opacity attributes (ablation)3D-GS · Train scene (Tanks&Temples)PSNR: 21.94 -> 21.60Hurt
quantize attributes (ablation)3D-GS · Playroom (Deep Blending)PSNR: 30.07 -> 30.48Improved
quantize opacity coefficients (ablation)3D-GS · novel view qualityfloaters / artifacts (qualitative)Improved
add progressive coarse-to-fine training (ablation)EAGLES · Bicycle (Mip-NeRF360)PSNR: 24.86 -> 25.07Improved
add progressive coarse-to-fine training (ablation)EAGLES · Train scene (Tanks&Temples)Number of Gaussians: 1.03M -> 0.85MImproved
increase densification interval to 175 (ablation)EAGLES · Train scene (Tanks&Temples)Number of Gaussians: 0.85M -> 0.64MImproved
add influence pruning stage (ablation)EAGLES · Train scene (Tanks&Temples)FPS: 202 -> 234Improved
add influence pruning stage (ablation)EAGLES · Train scene (Tanks&Temples)PSNR: 21.62 -> 21.65No clear effect
decrease progressive start scale below 0.3 (ablation)EAGLES · Truck scenePSNRHurt
use large 15x15 Gaussian filter instead of 5x5 for progressive scaling (ablation)EAGLES · progressive scaling variantsPSNR: 23.41dB -> 23.17dBHurt
EAGLES vs 3D-GS runtime memoryEAGLES · Bicycletraining GPU memory: 17.4G -> 10GImproved

Later papers that compared with this method

4 later accepted papers report EAGLES as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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