AI Paper Atlas

Research map / 3D vision / Human pose estimation

HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation

Yulin Wang, Mengting Hu, Hongli Li, Chen Luo

ICCV 2025 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 5 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 hierarchical binary coordinate encoding (HBCE) in place of ZebraPose surface-region encoding (ablation)ZebraPose · IC-BINAR of ADD(-S): 55.85 -> 56.82Improved
replace HBCE with hierarchical continuous coordinate encoding (HCCE, h3) (ablation)HBCE · IC-BINAR of ADD(-S): 56.82 -> 61.95Improved
add hierarchy to continuous coordinate encoding (CCE to HCCE) (ablation)CCE · IC-BINAR of ADD(-S): 55.42 -> 61.35Improved
add single-histogram loss weight adjustment (h1) to HCCE (ablation)HCCE · IC-BINAR of ADD(-S): 61.35 -> 60.44Hurt
add multi-histogram loss weight adjustment (h3) to HCCE (ablation)HCCE · IC-BINAR of ADD(-S): 61.35 -> 61.95Improved
add multi-histogram weight adjustment (h3) over single histogram (h1) (ablation)HCCE · IC-BINAR of ADD-S: 65.23 -> 68.30Improved
predict back surface in addition to front surface (bf) (ablation)front-only (f) · LM-O/TUD-L/IC-BINAP of BOP score: 82.2 -> 82.6Improved
predict front surface in addition to back surface (bf) (ablation)back-only (b) · LM-O/TUD-L/IC-BINAP of BOP score: 81.3 -> 82.6Improved
add uniform sampling between front and back surfaces (bfu) (ablation)bf · LM-O/TUD-L/IC-BINAP of BOP score: 82.6 -> 83.3Improved
use ultra-dense correspondences (bfu) instead of front only (ablation)front-only (f) · LM-O/TUD-L/IC-BINAP of BOP score: 82.2 -> 83.3Improved
HccePose(BF) vs ZebraPose on RGB 6D localizationZebraPose · BOP core (RGB)AR(AP) Core: 74.9 -> 77.3Improved
HccePose(BF) vs ZebraPose on 2D segmentationZebraPose · BOP core (RGB)AR(AP) Core: 61.9 -> 65.6Improved

Earlier methods this paper compares with

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