AI Paper Atlas

Research map / 3D vision / Face and shape

PlaneTR: Structure-Guided Transformers for 3D Plane Recovery

Bin Tan, Nan Xue, Song Bai, Tianfu Wu, Gui-Song Xia

ICCV 2021 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 49 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 line segment tokens to the plane decoder (ablation)PlaneTR · ScanNetplane recall @0.10m: 35.71 -> 38.44Improved
add line segment tokens to the plane decoder (ablation)PlaneTR · ScanNetVI: 0.885 -> 0.831Improved
add auxiliary plane center prediction (ablation)PlaneTR · ScanNetplane recall @0.10m: 35.71 -> 38.07Improved
add auxiliary plane center prediction (ablation)PlaneTR · ScanNetVI: 0.885 -> 0.778Improved
add plane center prediction on top of line segments (ablation)PlaneTR · ScanNetplane recall @0.10m: 38.44 -> 40.74Improved
add line segments on top of plane center prediction (ablation)PlaneTR · ScanNetplane recall @0.10m: 38.07 -> 40.74Improved
increase plane queries from 20 to 30 (ablation)PlaneTR · ScanNetplane recall @0.10m: 40.74 -> 40.58No clear effect
increase plane queries from 20 to 40 (ablation)PlaneTR · ScanNetplane recall @0.10m: 40.74 -> 39.25Hurt
use PlaneTR instead of PlaneAEPlaneTR vs PlaneAE · ScanNetVI: 1.025 -> 0.767Improved
use PlaneTR instead of PlaneAEPlaneTR vs PlaneAE · NYUv2-PlaneVI: 1.393 -> 1.110Improved
use PlaneTR instead of PlaneRCNN for depthPlaneTR vs PlaneRCNN · NYUv2 depthRel: 0.183 -> 0.195Hurt
use PlaneTR instead of PlaneAE for depthPlaneTR vs PlaneAE · NYUv2 depthdelta1: 61.3 -> 63.3Improved

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