AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning Feature Descriptors using Camera Pose Supervision

Qianqian Wang, Xiaowei Zhou, Bharath Hariharan, Noah Snavely

ECCV 2020 · 3D vision › Human pose estimation · approach: Category-level object pose estimation

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 CAPS descriptors with SuperPoint keypoints instead of SuperPoint descriptorsSuperPoint keypoints · HPatches homography estimation (eps=1px)corner correctness accuracy (%): 37.4 -> 44.8Improved
use CAPS descriptors with SIFT keypoints instead of SIFT descriptorsSIFT keypoints · HPatches homography estimation (eps=3px)corner correctness accuracy (%): 68.1 -> 72.2Improved
use CAPS descriptors with SIFT keypoints instead of SIFT descriptorsSIFT keypoints · HPatches homography estimation (eps=1px)corner correctness accuracy (%): 40.5 -> 34.6Hurt
use CAPS with SuperPoint keypoints instead of SuperPoint descriptorsSuperPoint keypoints · MegaDepth relative pose (hard)rotation accuracy (%): 24.5 -> 38.1Improved
use CAPS with SIFT keypoints instead of SIFT with ratio testSIFT keypoints · MegaDepth relative pose (hard)rotation accuracy (%): 20.8 -> 36.8Improved
use CAPS with SuperPoint keypoints instead of R2D2R2D2 · ScanNet relative pose (dframe=60)rotation accuracy (%): 62.9 -> 59.3Hurt
use CAPS instead of GeoDesc/SOSNet descriptorsSOSNet · ETH benchmark Madrid Metropolis (# registered images)registered images: 844 -> 851No clear effect
train with camera-pose epipolar loss instead of ground-truth correspondence triplet loss (ablation)CAPS · HPatches ablation (MMA, PCK)MMA and PCKImproved
train with ground-truth correspondences (L2 loss) instead of camera pose only (ablation)CAPS · HPatches ablation (MMA, PCK)MMA and PCKMixed
add cycle consistency loss (ablation)CAPS · HPatches ablation (MMA, PCK)MMA and PCKImproved
train with cycle consistency loss only, no epipolar loss (ablation)CAPS · HPatches ablation (MMA, PCK)MMA and PCKHurt
add coarse-to-fine architecture (ablation)CAPS · HPatches ablation (MMA, PCK)MMA and PCKImproved

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