AI Paper Atlas

Research map / 3D vision / Depth and stereo

P²Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation

Zehao Yu, Lei Jin, Shenghua Gao

ECCV 2020 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion

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 patch-match multi-view photometric consistency to the texture-weighted baseline (ablation)P2Net · NYUv2 depthrms: 0.786 -> 0.612Improved
add patch-match multi-view photometric consistency to the texture-weighted baseline (ablation)P2Net · NYUv2 depthdelta<1.25: 0.628 -> 0.758Improved
add plane regularization on top of patch-match (ablation)P2Net · NYUv2 depthrms: 0.612 -> 0.599Improved
add plane regularization on top of patch-match (ablation)P2Net · NYUv2 depthdelta<1.25: 0.758 -> 0.772Improved
use SURF keypoints instead of DSO (ablation)P2Net · NYUv2 depthrms: 0.612 -> 0.622No clear effect
use patch pattern N=3 instead of N=1 (ablation)P2Net · NYUv2 depthrms: 0.629 -> 0.612Improved
increase patch pattern N from 3 to 4 (ablation)P2Net · NYUv2 depthrms: 0.612 -> 0.634Hurt
use 5-frame input instead of 3-frameP2Net · NYUv2 depthrms: 0.599 -> 0.561Improved
add left-right flip test augmentation (PP)P2Net · NYUv2 depthrms: 0.561 -> 0.553Improved
use P2Net instead of MovingIndoor, zero-shot on ScanNetP2Net · ScanNet depthrms: 0.483 -> 0.420Improved
use P2Net instead of Monov2 on KITTIP2Net · KITTI depthrel: 0.115 vs 0.126Hurt

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