AI Paper Atlas

Research map / Point clouds / Segmentation and detection

VaPiD: A Rapid Vanishing Point Detector via Learned Optimizers

Shichen Liu, Yichao Zhou, Yajie Zhao

ICCV 2021 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 20 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 efficient conic convolutions to the vanishing point proposal network (ablation)VPPN · SU3 wireframerecall at 6 deg: 89.53 -> 99.00Improved
add efficient conic convolutions to the vanishing point proposal network (ablation)VPPN · SU3 wireframerecall at 2 deg: 33.20 -> 56.20Improved
add efficient conic convolutions to the vanishing point proposal network (ablation)VPPN · SU3 wireframemean angle error: 0.554° -> 0.146°Improved
increase inference refinement steps from 4 to 8 (ablation)NVPO · SU3 wireframemedian angle error: 0.145° -> 0.088°Improved
increase inference refinement steps from 8 to 24 (ablation)NVPO · SU3 wireframemedian angle error: 0.088° -> 0.085°No clear effect
increase inference refinement steps from 4 to 24 (ablation)NVPO · SU3 wireframeFPS: 26 -> 7Hurt
increase inference refinement steps from 4 to 8 (ablation)NVPO · SU3 wireframeAA at 0.1 deg: 15.1 -> 26.6Improved
use VaPiD instead of NeurVPSvanishing point detector · HoliCitymean angle error: 8.32° -> 3.00°Improved
use VaPiD instead of NeurVPSvanishing point detector · Natural SceneAA at 1 deg: 29.1 -> 24.6Hurt
use VaPiD instead of NeurVPSvanishing point detector · Natural SceneAA at 10 deg: 85.5 -> 87.4Improved
use VaPiD instead of CONSACvanishing point detector · NYU-VPAUC at 10 deg: 65.0 -> 69.1Improved
use VaPiD instead of NeurVPSvanishing point detector · SU3 wireframemedian angle error: 0.090° -> 0.088°Improved

Later papers that compared with this method

1 later accepted paper reports VaPiD as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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