AI Paper Atlas

Research map / Detection and segmentation / CNN features

Joint Map and Symmetry Synchronization

Yifan Sun, Zhenxiao Liang, Xiangru Huang, Qixing Huang

ECCV 2018 · Detection and segmentation › CNN features · approach: Box regression and loss design · 14 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
jointly synchronize maps and symmetry instead of using input symmetry detection [6]Stool images · Stool% correspondences within 0.1d: 71.2 -> 84.5Improved
jointly synchronize maps and symmetry instead of using input symmetry detection [6]TrashContainer images · TrashContainer% correspondences within 0.1d: 68.7 -> 81.2Improved
jointly synchronize maps and symmetry instead of input detection [13]Stool images · Stool% correspondences within 0.1d: 65.9 -> 79.8Improved
jointly synchronize maps and symmetry instead of input detection [13]TrashContainer images · TrashContainer% correspondences within 0.1d: 63.1 -> 77.4Improved
joint symmetry detection over collection instead of input symmetry [25]SHREC07 shapes · SHREC07-Watertight Octopus% correspondences within 0.1d: 52.4 -> 76.1Improved
joint symmetry detection over collection instead of input symmetry [40]SHREC07 shapes · SHREC07-Watertight Octopus% correspondences within 0.1d: 48.3 -> 68.0Improved
use symmetry-aware joint synchronization instead of Zhou15bjoint map optimization · Stool% correspondences within 0.1d: 64.6 -> 80.6Improved
use symmetry-aware joint synchronization instead of Huang14joint map optimization · TrashContainer% correspondences within 0.1d: 62.8 -> 75.2Improved
use ours instead of Zhou15b on Sedan (no symmetry, identity diagonal)joint map optimization · Sedan% correspondences within 0.1d: 87.7 -> 91.2Improved
use ours in original space on SHREC07 shapes vs Huang14joint map optimization · SHREC07-Watertight (mean)% correspondences within 0.1d: 61.7 -> 65.9Improved
symmetry-aware joint synchronization vs input on Plane (original space)joint map optimization · SHREC07-Watertight Plane% correspondences within 0.1d: 30.2 -> 38.0Improved

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