AI Paper Atlas

Research map / 3D vision / Gaussian splatting

DASAM3D: A Unified Foundation Model for Enhanced 3D Scene Reconstruction and Segmentation

RONNY XAVIER VELASTEGUI SANDOVAL, Max Pfingsthorn, Sezer Karaoglu, Theo Gevers

ECCV 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views

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
fuse SAM 3D layout into DA3DA3 · MipNeRF-360 (6 scenes) 3D reconstructionChamfer Distance (cm): 10.76 -> 10.10Improved
fuse SAM 3D layout into DA3DA3 · DL3DV-10K NVSPSNR (dB): 26.64 -> 27.08Improved
fuse SAM 3D layout into DA3DA3 · MipNeRF-360 (6 scenes) NVSLPIPS: 0.237 -> 0.234No clear effect
add per-object local alignment after global alignment (ablation)DASAM3D · MipNeRF-360 RoomChamfer Distance (cm): 11.41 -> 9.86Improved
add per-object local alignment after global alignment (ablation)DASAM3D · MipNeRF-360 CounterF-score (%): 55.2 -> 63.4Improved
add per-object local alignment after global alignment (ablation)DASAM3D · MipNeRF-360 KitchenF-score (%): 56.7 -> 64.1Improved
increase number of SAM 3D objects K from 1 to 8 (ablation)DASAM3D · MipNeRF-360 CounterChamfer Distance (cm): 9.41 -> 7.58Improved
add quality-based object filtering (ablation)DASAM3D · MipNeRF-360 CounterPSNR (dB): 24.78 -> 25.14Improved
add quality-based object filtering (ablation)DASAM3D · MipNeRF-360 CounterN-MAE (deg): 17.4 -> 15.6Improved
add depth loss in Stage 3 (ablation)DASAM3D · MipNeRF-360 CounterAbs Rel: 0.142 -> 0.098Improved
add normal loss in Stage 3 (ablation)DASAM3D · MipNeRF-360 CounterN-MAE (deg): 21.3 -> 15.6Improved
add RGB consistency loss in Stage 3 (ablation)DASAM3D · MipNeRF-360 CounterPSNR (dB): 24.23 -> 25.14Improved

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