AI Paper Atlas

Research map / 3D vision / 3D generation

FROSS: Faster-Than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Images

Hao-Yu Hou, Chun-Yi Lee, Motoharu Sonogashira, Yasutomo Kawanishi

ICCV 2025 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 9 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 ground-truth 2D scene graphs instead of predicted (ablation)FROSS · 3DSSGrelationship recall: 27.9 -> 55.8Improved
use ground-truth 2D scene graphs instead of predicted (ablation)FROSS · 3DSSGobject mRecall: 63.8 -> 93.3Improved
use ground-truth 2D scene graphs instead of predicted (ablation)FROSS · ReplicaSSGrelationship recall: 22.3 -> 67.6Improved
use ground-truth 2D scene graphs instead of predicted (ablation)FROSS · ReplicaSSGobject recall: 26.1 -> 89.1Improved
use ORB-SLAM3 estimated trajectories instead of ground-truth poses (ablation)FROSS · ReplicaSSGrelationship recall: 22.3 -> 22.7No clear effect
use ORB-SLAM3 estimated trajectories instead of ground-truth poses (ablation)FROSS · ReplicaSSGobject recall: 26.1 -> 25.8No clear effect
raise Hellinger merge threshold from 0.65 to 0.85 (ablation)FROSS · threshold sweeprelationship recall: 16.5 -> 30.0Improved
raise Hellinger merge threshold from 0.65 to 0.85 (ablation)FROSS · threshold sweepobject recall: 69.8 -> 61.9Hurt
raise Hellinger merge threshold from 0.85 to 0.9 (ablation)FROSS · threshold sweeprelationship recall: 30.0 -> 29.3Hurt
replace EGTR object detector with RT-DETR (ablation)EGTR · ReplicaSSGlatency (ms): 14.6 -> 6.82Improved
replace EGTR object detector with RT-DETR (ablation)EGTR · Visual GenomeR@50: 30.2 -> 22.0Hurt
replace EGTR object detector with RT-DETR (ablation)EGTR · ReplicaSSGAP@50: 21.2 -> 23.8Improved

Later papers that compared with this method

2 later accepted papers report FROSS as a baseline in their results tables; 2 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