AI Paper Atlas

Research map / 3D vision / 3D generation

Multi-Plane Program Induction with 3D Box Priors

Yikai Li, Jiayuan Mao, Xiuming Zhang, Bill Freeman, Josh Tenenbaum, Noah Snavely, Jiajun Wu

NeurIPS 2020 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 5 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 box-program induction with 3D box priors instead of PlaneRCNNBPI · Corridor plane segmentationIoU: 0.52 -> 0.84Improved
use BPI instead of Huang et al. for plane segmentationBPI · Corridor plane segmentationIoU: 0.30 -> 0.84Improved
use BPI instead of Huang et al. for building plane segmentationBPI · Building plane segmentation (original)IoU: 0.73 -> 0.86Improved
use BPI instead of PlaneRCNN for building plane segmentationBPI · Building plane segmentation (original)IoU: 0.63 -> 0.86Improved
corrupt the input image before segmentationBPI · Plane segmentationIoU: 0.84 -> 0.84No clear effect
BPI-guided PatchMatch instead of plain PatchMatch for inpaintingPatchMatch · Corridor inpaintingL1 mean: 53.12 -> 38.45Improved
BPI-guided PatchMatch instead of GatedConv for inpaintingGatedConv · Corridor inpaintingPSNR: 32.32 -> 34.21Improved
BPI instead of GatedConv on corridor LPIPSGatedConv · Corridor inpaintingLPIPS: 0.0153 -> 0.0170Hurt
BPI instead of Huang et al. on building inpaintingHuang et al. · Building inpaintingL1 mean: 26.10 -> 26.43No clear effect
BPI instead of GatedConv on building inpaintingGatedConv · Building inpaintingPSNR: 29.54 -> 34.86Improved
use box prior to reduce program search space (ablation)BPI · Search time on corridor imagesspeedup: 23x fasterImproved
BPI instead of other extrapolation methods in user rankingBPI · Building image extrapolationpreference (%): 61%Improved

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