AI Paper Atlas

Research map / 3D vision / Human pose estimation

RelocNet: Continuous Metric Learning Relocalisation using Neural Nets

Vassileios Balntas, Shuda Li, Victor Prisacariu

ECCV 2018 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 241 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
learn descriptors with frustum overlap loss instead of ImageNet ResNet18 featuresretrieval descriptors · 7Scenes headsrelocalisation success rate: 48.6 % -> 70.33%Improved
learn descriptors with frustum overlap loss instead of ImageNet ResNet18 featuresretrieval descriptors · 7Scenes stairsrelocalisation success rate: 32.5% -> 62.77%Improved
learn descriptors with frustum overlap loss instead of Places ResNet18 featuresretrieval descriptors · 7Scenes firerelocalisation success rate: 73.1% -> 79.01%Improved
use frustum overlap descriptors instead of PoseNet penultimate featuresretrieval descriptors · 7Scenes headsrelocalisation success rate: 29.1% -> 70.33%Improved
use frustum overlap descriptors instead of Fernsretrieval descriptors · 7Scenes headsrelocalisation success rate: 30.63% -> 70.33%Improved
train retrieval descriptors on more training sequences (10, 50, 100) (ablation)RelocNet descriptors · 7Scenes headsrelocalisation success rateImproved
fuse k=5 nearest neighbours instead of the single nearest neighbour (ablation)RelocNet pose estimation · 7Scenes chessmedian error: 0.12m, 4.14 -> 0.12m, 3.95Improved
fuse k=5 nearest neighbours instead of the single nearest neighbour (ablation)RelocNet pose estimation · 7Scenes headsmedian error: 0.14m, 10.5 -> 0.13m, 10.5Improved
fuse k=5 nearest neighbours instead of the single nearest neighbour (ablation)RelocNet pose estimation · 7Scenes stairsmedian error: 0.28m, 7.53 -> 0.27m, 7.31Improved
train and test RelocNet on the same 7Scenes sequence instead of ScanNet transferRelocNet · 7Scenes chessmedian translation error: 0.21m -> 0.12mImproved
use RelocNet trained on ScanNet instead of PoseNet GeometricRelocNet · 7Scenes stairsmedian translation error: 0.35m -> 0.33m; chess 0.13m -> 0.21mMixed

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