AI Paper Atlas

Research map / 3D vision / 3D generation

Multiple-gaze geometry: Inferring novel 3D locations from gazes observed in monocular video

Ernesto Brau, Jinyan Guan, Tanya Jeffries, Kobus Barnard

ECCV 2018 · 3D vision › 3D generation · approach: Semantic scene completion · 23 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 head pose inference (ablation)MGG · own datasethead yaw MOTP (deg): 67.3 -> 28.1Improved
add head pose inference (ablation)MGG · own datasethead pitch MOTP (deg): 19.3 -> 16.8Improved
add head pose inference (ablation)MGG · own datasetVFoA accuracy: 0.14 -> 0.48Improved
add head pose inference (ablation)MGG · own datasetobject discovery recall: 0.10 -> 0.48Improved
add head pose inference (ablation)MGG · own datasetMOTA position: 0.93 -> 0.95No clear effect
add joint VFoA inference (ablation)MGG · own datasetVFoA accuracy: 0.31 -> 0.48Improved
add joint VFoA inference (ablation)MGG · own datasetobject discovery recall: 0.14 -> 0.48Improved
add joint VFoA inference (ablation)MGG · own datasetobject discovery precision: 0.15 -> 0.59Improved
add joint inference over static objects instead of gaze-intersection histogram (ablation)MGG · own datasetVFoA accuracy: 0.13 -> 0.48Improved
add joint inference over static objects instead of gaze-intersection histogram (ablation)MGG · own datasetobject discovery precision: 0.12 -> 0.59Improved
add joint inference over head pose, VFoA, objects to tracking model of [13]tracking model · TUD (mean)MOTA: 0.78 -> 0.82Improved
add joint inference over head pose, VFoA, objects to tracking model of [13]tracking model · TUD (mean)MOTP: 0.23 -> 0.08Improved

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