AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning Neural Volumetric Pose Features for Camera Localization

Jingyu Lin, Jiaqi Gu, Bojian Wu, Lubin Fan, Renjie Chen, Ligang Liu, Jieping Ye

ECCV 2024 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 10 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
supervise with PoseMap features (L_posemap) instead of no pose feature (ablation)PMNet (DFNet baseline) · Kings (Cambridge)median translation error (m): 1.03 -> 0.68Improved
use raw NeRF feature map (NeRFMap) supervision instead of PoseMap (ablation)PMNet · Kings (Cambridge)median rotation error (deg): 2.94 -> 5.76Hurt
add L_image feature adapter loss (ablation)PMNet · Kings (Cambridge)median translation error (m): 0.75 -> 0.68Improved
add RVS loss for novel view augmentation (ablation)PMNet · Kings (Cambridge)median translation error (m): 0.94 -> 0.68Improved
add L_posemap during online refinement with unlabelled data (ablation)PMNet_ud · Kings (Cambridge)median translation error (m): 0.39 -> 0.31Improved
PMNet_ud versus DFNet_dm using unlabelled dataPMNet_ud · Cambridge Landmarks (average)median translation error (m): 0.39 -> 0.31Improved
PMNet_ud versus DFNet_dm on outlier test viewsPMNet_ud · Cambridge Kings top-30 outliersmean translation error (m): 1.94 -> 0.85Improved
reduce training data to 25 and 50 percent (ablation)PMNet versus DFNet · Kings (Cambridge)accuracyImproved
add PoseMap loss versus DFNet, cost in APR training timePMNet · Kings training timeAPR training hours: 6.0 -> 7.5Hurt
PMNet without post-processing versus iterative refinement methodsPMNet · Cambridge Landmarks (average)median translation error (m): 0.90 vs 0.35Hurt

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