AI Paper Atlas

Research map / 3D vision / Depth and stereo

Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences

Mohammed E. Fathy, Quoc-Huy Tran, M. Zeeshan Zia, Paul Vernaza, Manmohan Chandraker

ECCV 2018 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 50 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
use shallow conv2 features instead of deep conv5 features at small thresholdsingle-layer net · KITTI Flow 2015 PCK@5pxPCK: 61.78% -> 73.89%Improved
use deep conv5 features instead of conv2 at large thresholdsingle-layer net · KITTI Flow 2015 PCK@15pxPCK: 81.36% -> 87.57%Improved
add hypercolumn fusion over conv5-netconv5-net · KITTI Flow 2015 PCK@5pxPCK: 61.78% -> 69.41%Improved
hypercolumn fusion versus plain conv2 featuresconv2-net · KITTI Flow 2015 PCK@5pxPCK: 73.89% -> 69.41%Hurt
add hierarchical matching with deep-to-shallow refinementconv2-net · KITTI Flow 2015 PCK@5pxPCK: 73.89% -> 80.17%Improved
train on MPI Sintel instead of KITTI (cross-domain) (ablation)HiLM (conv2+conv5) · KITTI Flow 2015 PCK@5pxPCK: 79.11% -> 72.37%Hurt
HiLM trained on Sintel versus fusion baseline trained on KITTIHiLM (conv2+conv5) · KITTI Flow 2015 PCK@5pxPCK: 69.41% -> 72.37%Improved
add hierarchical metric learning and matching versus UCNUCN · KITTI Flow 2015 PCK@2pxPCK: 29.38% -> 43.26%Improved
switch backbone from VGG-M to GoogLeNet (ablation)HiLM · KITTI Flow 2015 PCK@10pxPCK: 85.08% -> 85.18%No clear effect
add deep supervised shallow features to HiL(conv8) (ablation)3D CNN · 3DMatch PCK@9cmPCK: 20.78% -> 21.50%Improved
add shallow refinement on top of deep features (HiLM)3DMatch · 3DMatch PCK@9cmPCK: 22.04% -> 24.36%Improved
use HiLM matches with EpicFlow interpolation versus semantic-prior methodsHiLM · KITTI Flow 2015 Fl-fgoutlier %: 8.75% vs 21.79%Mixed

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