AI Paper Atlas

Research map / 3D vision / 3D generation

Virtual Training for a Real Application: Accurate Object-Robot Relative Localization Without Calibration

Vianney Loing, Renaud Marlet, Mathieu Aubry

IJCV 2018 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 24 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
Predict x, y and theta with separate 1D bins instead of joint 2D (x,y) bins (ablation)coarse CNN · Coarse x, lab, 1 camerasuccess e_x <= 60mm: 6.1 -> 98.7Improved
Add theta and y heads to the 1D x network (joint training) (ablation)coarse CNN · Coarse x, lab, 1 camerasuccess e_x <= 60mm: 97.0 -> 98.7Improved
Replace single-step localization with three-step virtual close-up (ablation)pose CNN · Lab dataset, 1 camerasuccess e_x <= 5mm: 20.5 -> 61.1Improved
Replace single-step localization with three-step virtual close-up (ablation)pose CNN · Lab dataset, 1 camerajoint success: 2.8 -> 36.9Improved
Aggregate 3 cameras and 2 clamp positions (ablation)three-step · Lab datasetjoint success: 36.9 -> 79.0Improved
Aggregate 3 cameras for clamp P1 x estimate (ablation)fine CNN · Lab datasetx error (mm): 7.5 ± 16.0 -> 3.4 ± 7.6Improved
Aggregate both clamp orientations (ablation)fine CNN, all cameras · Lab datasetx error (mm): 3.4 ± 7.6 -> 2.3 ± 1.8Improved
Move from lab to field conditions (dirt, gravel)three-step, 3 cameras 2 clamps · Fine posejoint success: 79.9 -> 70.2Hurt
Move from lab to adversarial conditions (paper distractors)three-step, 3 cameras 2 clamps · Fine posejoint success: 79.9 -> 45.1Hurt
Move from synthetic to real lab imagesfine CNN, 1 camera · Fine posesuccess e_x <= 5mm: 85.3 -> 62.8Hurt
Move from synthetic to real lab imagesfine CNN, 1 camera · Fine posesuccess e_theta <= 2deg: 68.4 -> 83.2Improved
Use three-step with aggregation instead of ArUco marker on blockthree-step · Lab datasetsuccess e_x <= 5mm: 88.4 -> 90.8No clear effect

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