AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Gaussian Grouping: Segment and Edit Anything in 3D Scenes

Mingqiao Ye, Martin Danelljan, Fisher Yu, Lei Ke

ECCV 2024 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 338 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 3D regularization loss with K=5 nearest neighbors (ablation)Gaussian Grouping · Mip-NeRF 360 Kitchen object removalRAcc: 41.2% -> 76.6%Improved
increase K from 5 to 10 (ablation)3D regularization loss · Mip-NeRF 360 Kitchen object removalRAcc: 76.6% -> 77.8%No clear effect
add 3D Identity/Regularization loss to 2D identity loss (ablation)Gaussian Grouping · Bear inpaintingqualitativeImproved
use video-tracker mask association instead of cost-based linear assignment (ablation)Gaussian Grouping · 2K training iterationstraining time: 1 hour -> 1 minuteImproved
joint training of Identity Encoding with Gaussian SplattingGaussian Splatting · Mip-NeRF 360 (7 scenes)PSNR: 28.69 -> 28.43No clear effect
double Identity Encoding dimension from 16 to 32 (ablation)Gaussian Grouping · Mip-NeRF 360reconstruction quality and training time: training 1.3 times slowerNo clear effect
use Gaussian Grouping instead of SA3D for segmentationSA3D · LERF-Mask ramenmIoU: 7.4 -> 77.0Improved
use Gaussian Grouping instead of Panoptic LiftingPanoptic Lifting · Replica panopticmIoU (%): 66.22 -> 71.15Improved

Later papers that compared with this method

19 later accepted papers report Gaussian Grouping as a baseline in their results tables; 17 of them report a better number on most of the results they share with it.

11 more not listed.

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