AI Paper Atlas

Research map / 3D vision / 3D generation

UniMapping: Unified SLAM Framework for Map-Centric Embodied Perception

Xiaze Zhang, Ziheng Ding, Yuejie Zhang, lifeng chen, Rui Feng

ICML 2026 · 3D vision › 3D generation · approach: Semantic scene completion

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 Spatial Fusion to UniMapping detection (ablation)UniMapping · ScanNet detectionmAP25: 57.7 -> 60.8Improved
add Spatial Fusion to UniMapping segmentation (ablation)UniMapping · SemanticKITTImIoU: 53.7 -> 60.3Improved
use Temporal Fusion (10-frame window) instead of Spatial Fusion (ablation)UniMapping · SemanticKITTImIoU: 53.7 -> 53.8No clear effect
use Spatial Fusion instead of Temporal Fusion (ablation)UniMapping · ScanNet detectionmAP25: 59.2 -> 60.8Improved
replace cross attention with SADT in descriptor extraction (ablation)UniMapping · ScanNet SLAM seq 000 (25% train)ATE (cm): 21.6 -> 13.4Improved
replace vanilla deformable attention with SADT (ablation)UniMapping · ScanNet SLAM seq 059ATE (cm): 27.1 -> 14.9Improved
use SADT instead of simple interpolation (ablation)UniMapping · ScanNet SLAM seq 000ATE (cm): 14.0 -> 13.4Improved
use cross attention for spatial fusion instead of none (ablation)UniMapping · ScanNet detection (25% train)mAP25: 44.09 -> 41.29Hurt
use multi-scale spatial aggregation instead of deformable attention for fusion (ablation)UniMapping · ScanNet detection (25% train)mAP25: 46.27 -> 48.84Improved
add pose noise of 15 cm to Spatial Fusion (ablation)UniMapping · ScanNet detectionmAP25: decreases by 1.2% absoluteNo clear effect
distance-based map pruning (5 m) (ablation)UniMapping · map memorymap size, ATE: 61 MB -> 31 MB; ATE up approx 8%Mixed
use UniMapping instead of best specialized SLAM on ScanNet seq 000UniMapping · ScanNet SLAMATE (cm): 4.2 -> 13.7Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 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