AI Paper Atlas

Research map / 3D vision / 3D generation

Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images

Bo Zhou, Qiuxia Lai, Zeren Sun, Xiangbo Shu, Yazhou Yao, Wenguan Wang

CVPR 2026 · 3D vision › 3D generation · approach: Semantic scene completion · 0 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
add self-supervised appearance learning (ablation)UniSplat · ScanNet ablationmIoU: 0.5263 -> 0.5625Improved
add dual masking (ablation)UniSplat · ScanNet ablationPSNR: 24.74 -> 25.65Improved
add dual masking (ablation)UniSplat · ScanNet ablationmIoU: 0.5462 -> 0.5625Improved
add coarse-to-fine Gaussian splatting (ablation)UniSplat · ScanNet ablationmIoU: 0.5374 -> 0.5625Improved
add pose-conditioned recalibration loss (ablation)UniSplat · ScanNet ablationPSNR: 24.35 -> 25.65Improved
add pose-conditioned recalibration loss (ablation)UniSplat · ScanNet ablationAbs Rel: 3.52 -> 3.10Improved
add semantic distillation loss (ablation)UniSplat · ScanNet ablationmIoU: 0.0214 -> 0.5625Improved
add geometric prior loss (ablation)UniSplat · ScanNet ablationAbs Rel: 3.59 -> 3.10Improved
use geometry-aware decoder mask (3D GS, 0.50) instead of random-only masking (ablation)UniSplat · ScanNet mask ablationmIoU: 0.5412 -> 0.5625Improved
raise encoder mask ratio from 0.50 to 0.75 (ablation)UniSplat · ScanNet mask ablationmIoU: 0.5625 -> 0.5284Hurt
add ScanNet++ training data (ablation)UniSplat · ScanNet data scalemIoU: 0.5603 -> 0.5625Improved
add RealEstate10K and DL3DV training data (ablation)UniSplat · ScanNet data scalemIoU: 0.5625 -> 0.5755Improved

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