AI Paper Atlas

Research map / 3D vision / Depth and stereo

Coarse-to-Fine Multi-Scene Pose Regression With Transformers

Yoli Shavit, Ron Ferens, Yosi Keller

TPAMI 2023 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 30 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
add coarse-to-fine classification-regression with centroid residuals and fine-tune from MS-Transformer initMS-Transformer · Cambridge Landmarksavg position error (m): 1.28 -> 0.98Improved
initialize from pretrained MS-Transformer (ablation)c2f-MS-Transformer · Cambridge Landmarksavg position error (m): 1.27 -> 0.98Improved
initialize from pretrained MS-Transformer (ablation)c2f-MS-Transformer · 7Scenesavg position error (m): 0.18 -> 0.17No clear effect
use EfficientNetB0 instead of ResNet50 backbone (ablation)c2f-MS-Transformer · 7Scenesposition/orientation error: 0.19 -> 0.18 m; 8.60 -> 7.55 degImproved
use EfficientNetB1 instead of EfficientNetB0 (ablation)c2f-MS-Transformer · 7Scenesposition/orientation error: 0.18 -> 0.17 m; 7.55 -> 7.26 degImproved
use coarse position map 14x14x112 with fine orientation map 28x28x40 instead of fine maps for both (ablation)c2f-MS-Transformer · 7Scenesavg position error (m): 0.22 -> 0.18Improved
use 7x7x320 position map instead of 14x14x112 (ablation)c2f-MS-Transformer · 7Scenesavg position error (m): 0.18 -> 0.19Hurt
use coarse orientation map 14x14x112 instead of 28x28x40 (ablation)c2f-MS-Transformer · 7Scenesavg orientation error (deg): 7.55 -> 7.96Hurt
increase encoder/decoder layers from 2 to 6 (ablation)c2f-MS-Transformer · 7Scenesavg orientation error (deg): 8.21 -> 7.55Improved
increase transformer dimension from 64 to 512 (ablation)c2f-MS-Transformer · 7Scenesavg orientation error (deg): 8.32 -> 7.21Improved
use 4 position/orientation clusters instead of 8 (ablation)c2f-MS-Transformer · Cambridge Landmarksavg position error (m): 1.69 -> 1.27Improved
use a single position cluster instead of more clusters (ablation)c2f-MS-Transformer · 7Scenesavg position error (m): 0.25 -> 0.18Improved

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