AI Paper Atlas

Research map / 3D vision / 3D generation

3D Scene Assertion Verification

Jun Lin, Jiayu Ding, Xiangtian Si, Xitong Cao, Lixin Hong, Zhang Chen, Chenxi Lv, Wenqian Wang

ICML 2026 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding

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 Early LPSS routing (ablation)backbone · 3DSAV test setaccuracy: 77.3 -> 81.9Improved
add Late LPSS routing (ablation)backbone · 3DSAV test setaccuracy: 77.3 -> 82.0Improved
combine both stages (full DualLPSS) (ablation)single-stage variants · 3DSAV test setaccuracy: 82.0 -> 82.5Improved
add intra-text structural strength (ablation)DualLPSS · 3DSAV test setaccuracy: 81.7 -> 82.5Improved
add intra-object structural strength (ablation)DualLPSS · 3DSAV test setaccuracy: 82.2 -> 82.5Improved
use Gumbel-Softmax instead of standard Softmax in routing (ablation)DualLPSS · 3DSAV test setaccuracy: 81.7 -> 82.5Improved
use Soft Top-2 instead of Hard Top-K routing (ablation)DualLPSS · 3DSAV test setaccuracy: 81.2 -> 82.5Improved
set subspace count K=8 instead of 6 (ablation)Early LPSS · 3DSAV test setaccuracy: -1.3%Hurt
set subspace count K=8 instead of 6 (ablation)Late LPSS · 3DSAV test setaccuracy: -1.0%Hurt
use DualLPSS instead of Chat-Scene3DSAV baselines · 3DSAV test setaccuracy: 80.5 -> 82.5Improved
use DualLPSS instead of Chat-Scene on converted ScanQAcross-dataset transfer · 3DSAV test setaccuracy: 70.9 -> 82.1Improved
use DualLPSS instead of Chat-Scene on Quantity assertions3DSAV per-type · 3DSAV test setQuantity accuracy: 95.3 -> 90.2Hurt

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