AI Paper Atlas

Research map / 3D vision / 3D generation

Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction

Mingfang Zhang, Jinglu Wang, Xiao Li, Yifei Huang, Yoichi Sato, Yan Lu

CVPR 2023 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 11 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
Use scene-adaptive structural planes instead of fixed fronto-parallel MPI layersS-MPI · ScanNet, n<30PSNR: 21.058 -> 23.604Improved
Use global proxy embeddings to enforce multi-view consistency (ablation)S-MPI, 100 queries · ScanNet, multi-view view synthesis ablationPSNR: 22.65 -> 23.11Improved
Increase query number from 25 to 100 while retaining MVC (ablation)S-MPI · ScanNet, multi-view view synthesis ablationPSNR: 22.97 -> 23.11Improved
Increase the input-view gap from 0 to 20 frames (ablation)S-MPI · ScanNet, planar recallRC^0.1m: 52.61 -> 52.95Improved
Increase the input-view gap from 20 to 40 frames (ablation)S-MPI · ScanNet, planar recallRC^0.1m: 52.95 -> 46.43Hurt
Increase planar area in the scene (ablation)S-MPI · ScanNet, view synthesisPSNR: 22.97 -> 24.52Improved
Set planar proxy count to zero, treating all regions as non-planar (ablation)S-MPI · ScanNet, view synthesisPSNR: 24.52 -> 21.10Hurt
Use S-MPI instead of PlaneMVSMulti-view reconstruction · ScanNetrmse: 0.186 -> 0.205Hurt

Earlier methods this paper compares with

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