AI Paper Atlas

Research map / 3D vision / 3D generation

One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Image

Pengfei Wang, Liyi Chen, Zhiyuan Ma, Yanjun Guo, Guowen Zhang, Lei Zhang

ICLR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 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
add Dual-LoRA training instead of naive concatenation (ablation)scaffold-guided NVS · WorldScore-adapted 40 scenesCamMC: 0.655 -> 0.401Improved
add Dual-LoRA training instead of naive concatenation (ablation)scaffold-guided NVS · WorldScore-adapted 40 scenesCLIP-I: 85.30 -> 89.51Improved
add memory condition at inference (ablation)Dual-LoRA NVS · WorldScore-adapted 40 scenesCamMC: 0.401 -> 0.389Improved
add memory condition at inference (ablation)Dual-LoRA NVS · WorldScore-adapted 40 scenesNIQE: 4.42 -> 4.43No clear effect
add bidirectional fusion (BF) module (ablation)panorama depth network · Matterport3DAbsRel: 0.1204 -> 0.1070Improved
add bidirectional fusion (BF) module (ablation)panorama depth network · Stanford2D3DAbsRel: 0.0797 -> 0.0675Improved
replace AnySplat with the VGGT-based scaffold networkscene generation pipeline · WorldScore-adapted 40 scenesCamMC: 0.616 -> 0.389Improved
replace AnySplat with the VGGT-based scaffold networkscene generation pipeline · WorldScore-adapted 40 scenesQ-Align: 3.61 -> 4.13Improved
condition SEVA on anchor viewsSEVA · WorldScore-adapted 40 scenesCamMC: 0.558 -> 0.460Improved
condition VMem on anchor viewsVMem · WorldScore-adapted 40 scenesCamMC: 0.998 -> 0.887Improved
condition VMem on anchor viewsVMem · WorldScore-adapted 40 scenesTransErr: 0.573 -> 0.613Hurt
fine-tune on target panorama datasetsfeed-forward 3DGS depth · Matterport3DAbsRel: 0.1070 -> 0.0391Improved

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