AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointAR: Efficient Lighting Estimation for Mobile Augmented Reality

Yiqin Zhao, Tian Guo

ECCV 2020 · Point clouds › Point cloud classification · approach: Point cloud detection and tracking · 38 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
learn from point cloud with PointConv instead of projected panorama with ResNet50 (ablation)PointAR · Matterport3D/Neural Illumination testSH coefficients l2 loss: 0.781 -> 0.633Improved
learn from point cloud with PointConv instead of projected panorama with ResNet50 (ablation)PointAR · Matterport3D/Neural Illumination testirradiance map l2 loss: 0.535 -> 0.433Improved
increase point cloud size from 512 to 1280 points (ablation)PointAR · Matterport3D/Neural Illumination testSH coefficients l2 loss: 0.668 -> 0.633Improved
increase point cloud size from 512 to 1280 points (ablation)PointAR · Matterport3D/Neural Illumination testirradiance map l2 loss: 0.479 -> 0.433Improved
increase point cloud size from 1024 to 1280 points (ablation)PointAR · Matterport3D/Neural Illumination testirradiance map l2 loss: 0.441 -> 0.433Improved
increase point cloud size from 768 to 1280 points (ablation)PointAR · Matterport3D/Neural Illumination testSH coefficients l2 loss: 0.660 -> 0.633Improved
increase point cloud size from 512 to 1280 points (ablation)PointAR · Model complexityMACs (M): 320 -> 790Hurt
increase point cloud size from 512 to 1280 points (ablation)PointAR · Model complexityparameters (M): 1.42 -> 1.42No clear effect
use PointAR point cloud pipeline instead of Garon et al. image networkPointAR vs Garon et al. · Matterport3D/Neural Illumination testirradiance map l2 loss: 0.63 -> 0.433Improved
use PointAR point cloud pipeline instead of Garon et al. image networkPointAR vs Garon et al. · Matterport3D/Neural Illumination testSH coefficients l2 loss: 1.10 -> 0.633Improved
use PointAR instead of Song et al. multi-stage networkPointAR vs Song et al. · Matterport3D/Neural Illumination testirradiance map l2 loss: 0.619 -> 0.433Improved
use PointAR instead of ResNet50 backbone in terms of costPointAR · Model complexityparameters (M): 25.56 -> 1.42Improved

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