AI Paper Atlas

Research map / Point clouds / Point cloud classification

Deep Vanishing Point Detection: Geometric Priors Make Dataset Variations Vanish

Yancong Lin, Ruben Wiersma, Silvia L. Pintea, Klaus Hildebrandt, Elmar Eisemann, Jan C. van Gemert

CVPR 2022 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 31 citations (OpenAlex)

Check 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 Hough Transform and spherical convolutions instead of the non-learning LSD and sphere-NMS baseline (ablation)Vanishing point detection on ScanNet-1% · ScanNet-1%accuracyImproved
Replace classic Canny edge features with learned image semantics (ablation)Hough Transform and spherical-convolution model · ScanNet-1%accuracyImproved
Backpropagate through the Hough Transform (ablation)Hough Transform and spherical-convolution model · ScanNet-1%accuracyImproved
Add spherical convolutions (ablation)Hough Transform model · ScanNet-1%accuracyImproved
Increase Hough angle sampling from 90 to 180 (ablation)Vanishing point detector · SU3-10%AA@3°: 77.1 -> 79.3Improved
Increase Gaussian sphere sampling from 8K to 32K points (ablation)Vanishing point detector · SU3-10%AA@3°: 73.3 -> 79.3Improved
Use multi-scale sampling rather than dense sphere sampling (ablation)Ours · Manhattan datasetsFPS: 5.5 -> 23.0Improved
Use multi-scale sampling (ablation)Ours · ScanNetAA@10°: 63.7 -> 62.4Hurt
Remove the Manhattan orthogonality constraint by using unknown focal length (ablation)Ours · ScanNetAA@10°: 63.7 -> 59.9Hurt
Use geometric priors in place of relying on learned dataset-specific patternsVanishing point detection · ScanNet reduced-data subsetsAA@10°Improved
Use geometric priors rather than NeurVPS for training with reduced dataVanishing point detection · SU3 reduced-data subsetsAA@10°Improved
Transfer from SU3 to ScanNet without dataset-specific tuningOurs versus CONSAC · ScanNet, trained on SU3AA@10°: 39.5 vs 27.2Improved

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