AI Paper Atlas

Research map / 3D vision / Human pose estimation

H4D: Human 4D Modeling by Learning Neural Compositional Representation

Boyan Jiang, Yinda Zhang, Xingkui Wei, Xiangyang Xue, Yanwei Fu

CVPR 2022 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 20 citations (OpenAlex)

Check 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 H4D instead of 4D-CR4D human representation · CAPE 4D reconstructionIoU: 62.9% -> 73.3%Improved
Use H4D instead of 4D-CR4D human representation · CAPE motion retargetingIoU: 47.3% -> 70.7%Improved
Use H4D instead of 4D-CR4D human representation · CAPE motion completionIoU: 76.6% -> 90.3%Improved
Use H4D instead of 4D-CR4D human representation · CAPE future predictionIoU: 64.0% -> 71.7%Improved
Combine the linear motion prior with learned per-frame compensation (ablation)H4D · CAPE motion recoverymotion accuracyImproved
Add Motion-Comp to the linear motion model (ablation)H4D · CAPE motion recoverymotion accuracyImproved
Add auxiliary-code-driven Shape-Comp (ablation)H4D · CAPE clothed mesh reconstructionPVEImproved
Use a GRU temporal encoder instead of modified PointNet (ablation)H4D · CAPE reconstructionreconstruction performanceImproved
Use GRU-based Shape-Comp instead of the naive CAPE decoderH4D auto-decoding · CAPE motion completion with noisy observationsPVEImproved
Keep VAE and adversarial loss in Shape-Comp (ablation)H4D · CAPE shape compensationreconstruction performanceHurt
Use H4D instead of 4D-CR-SMPL for forward shape and motion recoveryhuman body estimation · CAPE shape and motion recovery (forward)PA-MPJPE: 59.2 -> 38.4Improved
Use H4D instead of 4D-CR-SMPL for backward completionhuman body estimation · CAPE motion completion (backward)MPJPE: 67.3 -> 42.7Improved

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