AI Paper Atlas

Research map / 3D vision / Depth and stereo

PlaneRecTR: Unified Query Learning for 3D Plane Recovery from a Single View

Jingjia Shi, Shuaifeng Zhi, Kai Xu

ICCV 2023 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 13 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 plane-level depth prediction to unified query learning (ablation)PlaneRecTR · ScanNetplane offset error (mm): 166.85 -> 165.13Improved
add plane-level depth prediction to unified query learning (ablation)PlaneRecTR · ScanNetper-pixel depth recall @0.10m: 50.28 -> 53.07Improved
add explicit dense plane-level mask prediction (ablation)PlaneRecTR (-D) · ScanNetplane normal error (deg): 10.97 -> 10.27Improved
add plane-level mask prediction (ablation)PlaneRecTR (-D) · ScanNetplane offset error (mm): 177.69 -> 166.85Improved
add plane parameter and depth learning to segmentation model (ablation)PlaneRecTR (-P-D) · ScanNetplane segmentationNo clear effect
use separate pixel decoders for semantics and depth embeddings (ablation)PlaneRecTR · ScanNetperformanceNo clear effect
replace ResNet-50 with HRNet-32 backbonePlaneRecTR · NYUv2-Plane depthRel: 0.202 -> 0.178Improved
replace ResNet-50 with Swin-B backbonePlaneRecTR · ScanNetVI: 0.698 -> 0.651Improved
PlaneRecTR (ResNet-50) vs PlaneTR on NYUv2 planar depthPlaneRecTR · NYUv2-Plane depth (planar regions)delta1: 59.6 -> 59.5No clear effect

Later papers that compared with this method

2 later accepted papers report PlaneRecTR++ as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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