AI Paper Atlas

Research map / 3D vision / Gaussian splatting

IQGS: Instance Query-based Gaussian Segmentation

Yichao Gao, Xinyuan Liu, Yike Ma, Yucheng Zhang, Feng Dai

AAAI 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 0 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 focal loss (ablation)IQGS · LERFmIoU (%): 33.91 -> 59.36Improved
add dice loss (ablation)IQGS · LERFmIoU (%): 49.43 -> 59.36Improved
add 3D regularization loss (ablation)IQGS · 360 v2mIoU (%): 60.08 -> 72.02Improved
add 2D-3D consistency loss (ablation)IQGS · 360 v2mIoU (%): 66.17 -> 72.02Improved
use ID matching instead of Hungarian matching (ablation)IQGS · 360 v2mIoU (%): 58.21 -> 72.02Improved
supervise with binary masks instead of ID maps (ablation)IQGS · LERFmIoU (%): 40.02 -> 59.36Improved
increase query number Nq from 50 to 300 (D=16) (ablation)IQGS · 360 v2mIoU (%): 57.13 -> 72.02Improved
feature dimension D=16 instead of 8 or 32 (Nq=300) (ablation)IQGS · LERFmIoU (%): 52.68 -> 59.36Improved
lower lambda_mask from 20.0 to 10.0 (ablation)IQGS · LERFmIoU (%): 59.36 -> 51.15Hurt
raise lambda_dice from 1.0 to 2.0 (ablation)IQGS · LERFmIoU (%): 59.36 -> 56.52Hurt
lower lambda_reg from 1.0 to 0.5 (ablation)IQGS · 360 v2mIoU (%): 72.02 -> 70.34Hurt
apply Gaussian Grouping to 2DGS instead of 3DGSGaussian Grouping · mean mIoU over scenesmIoU (%): 57.17 -> 36.34Hurt

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