AI Paper Atlas

Research map / 3D vision / Gaussian splatting

ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting

Ruijie Zhu, Mulin Yu, Linning Xu, Lihan Jiang, Yixuan Li, Tianzhu Zhang, Jiangmiao Pang, Bo Dai

ICCV 2025 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 12 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
use one-hot ID encoding with classification loss instead of learnable Gaussian semantics (ablation)ObjectGS · LERF-Mask figurinesmIoU: 69.57 -> 88.19Improved
use one-hot ID encoding instead of object-independent constraints (ablation)ObjectGS · LERF-Mask figurinesmIoU: 37.48 -> 88.19Improved
use majority voting instead of probability-based voting for point ID initialization (ablation)ObjectGS · LERF-Mask figurinesmIoU: 84.46 -> 88.19Improved
use majority voting instead of correspondence-based voting (ablation)ObjectGS · LERF-Mask figurinesmIoU: 59.67 -> 88.19Improved
add semantic loss with weight 0.1 (ablation)ObjectGS · ReplicaPSNR: 40.19 -> 40.26Mixed
raise semantic loss weight to 1.00 (ablation)ObjectGS · ReplicaPSNR: 40.26 -> 35.43Hurt
object-aware anchors with discrete semantics versus Gaussian GroupingGaussian Grouping · ScanNet++ panoptic (7 scenes)IoU: 89.82 -> 95.38Improved
ObjectGS versus Gaga on figurinesLERF-Mask figurines · LERF-Mask figurinesmIoU: 90.7 vs 88.2Hurt
ObjectGS on many-object ScanNet++ scenes versus Gaussian Groupingtraining cost · ScanNet++ 3e8btraining time: 71 min -> 113 minHurt

Later papers that compared with this method

1 later accepted paper reports ObjectGS as a baseline in their results tables; 0 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 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