AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Multi-Scene Absolute Pose Regression With Transformers

Yoli Shavit, Ron Ferens, Yosi Keller

ICCV 2021 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 160 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 Transformer encoders/decoders for multi-scene regression instead of per-scene FC layers (MSPN)absolute pose regressor · Cambridge Landmarks (4 scenes, average)position/orientation error: 2.47/5.34 -> 1.28/2.73Improved
use Transformer encoders/decoders for multi-scene regression instead of MSPNabsolute pose regressor · 7Scenes (average)position/orientation error: 0.20/8.41 -> 0.18/7.28Improved
train one multi-scene model instead of single-scene modelsMS-Transformer · Cambridge Landmarksposition/orientation error: 1.43/2.85 -> 1.28/2.73Improved
train one multi-scene model instead of single-scene modelsMS-Transformer · 7Scenesposition/orientation error: 0.24/7.87 -> 0.18/7.28Improved
train jointly on both datasets (multi-dataset) instead of one datasetMS-Transformer · Cambridge Landmarksposition/orientation error: 1.28/2.73 -> 1.50/2.57Mixed
train jointly on both datasets (multi-dataset) instead of one datasetMS-Transformer · 7Scenesposition/orientation error: 0.18/7.28 -> 0.22/6.78Mixed
use EfficientNetB0 backbone instead of ResNet50 (ablation)MS-Transformer · 7Scenesposition/orientation error: 0.19/8.6 -> 0.18/7.28Improved
use EfficientNetB1 instead of EfficientNetB0 backbone (ablation)MS-Transformer · 7Scenesposition/orientation error: 0.18/7.28 -> 0.17/7.26No clear effect
sample position map at coarse 14x14x112 and orientation map at fine 28x28x40 instead of swapped (ablation)MS-Transformer · 7Scenesposition/orientation error: 0.22/7.47 -> 0.18/7.28Improved
use different resolutions for position and orientation maps instead of the same 14x14x112 map (ablation)MS-Transformer · 7Scenesposition/orientation error: 0.19/7.78 -> 0.18/7.28Improved
use 6 encoder/decoder layers instead of 2 (ablation)MS-Transformer · 7Scenesposition/orientation error: 0.19/7.48 -> 0.18/7.28Improved
use 4 encoder/decoder layers instead of 6 (ablation)MS-Transformer · 7Scenesorientation error: 7.28 -> 6.94No clear effect

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