AI Paper Atlas

Research map / 3D vision / Human pose estimation

SRPose: Two-view Relative Pose Estimation with Sparse Keypoints

Rui Yin, Yulun Zhang, Zherong Pan, Jianjun Zhu, Cheng Wang, Biao Jia

ECCV 2024 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 6 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 keypoint-similarity prior guidance to cross-attention (ablation)SRPose · Matterporttranslation <=1m accuracy (%): 69.6 -> 74.2Improved
use cross-attention instead of only self-attention (ablation)SRPose · Matterporttranslation <=1m accuracy (%): 26.1 -> 74.2Improved
add position encoder (ablation)SRPose · Matterporttranslation <=1m accuracy (%): 61.0 -> 74.2Improved
add intrinsic calibration of keypoint coordinates (ablation)SRPose · MegaDepthpose AUC@5: 1.5 -> 16.6Improved
replace robust estimator with direct regression from sparse keypointsmatcher-based pose estimation · ScanNet-1500total time (ms): 269.7 -> 28.5 (vs LightGlue)Improved
use SRPose instead of dense matcher DKM on ScanNetSRPose · ScanNet-1500pose AUC@20: 68.3 -> 56.8Hurt
use object prompt bounding box instead of depth and segmentation matchersSRPose · HO3DADD: 17.8 -> 36.4Improved
apply SRPose vs RoMa+DPT in relocalization precisionSRPose · Nianticrelocalization precision: 22.8 -> 16.9 precision; VCRE 45.6 -> 46.4Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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