AI Paper Atlas

Research map / 3D vision / Human pose estimation

Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields

Garvita Tiwari, Dimitrije Antić, Jan Eric Lenssen, Nikolaos Sarafianos, Tony Tung, Gerard Pons-Moll

ECCV 2022 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 95 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
use Pose-NDF instead of VPoser as priormotion denoising · Noisy AMASS (60 frames)per-vertex error (cm): 8.96 -> 7.96Improved
use Pose-NDF instead of HuMoR as priormotion denoising · Noisy AMASS (240 frames)per-vertex error (cm): 30.31 -> 8.46Improved
use Pose-NDF instead of VPosermotion denoising · AMASS (60 frames)per-vertex error (cm): 1.52 -> 0.59Improved
use Pose-NDF instead of VPoseroccluded leg fitting · AMASS occluded leg (60 frames)per-vertex error (cm): 2.53 -> 2.49No clear effect
use Pose-NDF instead of HuMoRoccluded shoulder fitting · AMASS occluded shoulder + upper arm (60 frames)per-vertex error (cm): 4.75 -> 7.63Hurt
use Pose-NDF instead of HuMoRoccluded arm+hand fitting · AMASS occluded arm+hand (240 frames)per-vertex error (cm): 10.25 -> 7.98Improved
use Pose-NDF instead of VPoser as prioroptimization-based pose estimation · EHFper-vertex error (mm): 60.34 -> 57.39Improved
add Pose-NDF prior to ExPose refinement (vs no prior) (ablation)ExPose + optimization · EHFper-vertex error (mm): 99.78 -> 53.81Improved
add Pose-NDF refinement on top of ExPoseExPose · EHFper-vertex error (mm): 54.76 -> 53.81Improved
use Pose-NDF instead of GAN-S in ExPose refinementExPose + optimization · EHFper-vertex error (mm): 54.09 -> 53.81Improved
use Pose-NDF instead of VPoser for pose generationpose generation · Pose generation (500 samples)average pairwise distance (cm): 23.13 -> 32.31Improved
use Pose-NDF instead of VPoser for pose generationpose generation · Pose generationself-intersecting faces (%): 2.10 -> 0.89Improved

Later papers that compared with this method

2 later accepted papers report Pose-NDF as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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