AI Paper Atlas

Research map / 3D vision / Human pose estimation

EventHPE: Event-Based 3D Human Pose and Shape Estimation

Shihao Zou, Chuan Guo, Xinxin Zuo, Sen Wang, Pengyu Wang, Xiaoqin Hu, Shoushun Chen, Minglun Gong, Li Cheng

ICCV 2021 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 65 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 inferred optical flow as extra inputDHP19 pose network · DHP19MPJPE (mm): 80.08 -> 76.76Improved
add inferred optical flow as extra inputDHP19 pose network · DHP19PA-MPJPE (mm): 74.55 -> 71.68Improved
add inferred optical flow as extra inputDHP19 pose network · DHP19PEL-MPJPE (mm): 131.73 -> 130.37No clear effect
add inferred optical flow as extra inputDHP19 pose network · DHP19PCKh@0.5: 0.80 -> 0.82Improved
add optical flow input and flow coherence loss (ablation)EventHPE · MMHPSDPA-MPJPE (mm): 49.43 -> 43.90Improved
add optical flow input and flow coherence loss (ablation)EventHPE · MMHPSDPVE (mm): 59.77 -> 53.90Improved
add flow coherence loss on top of flow input (ablation)EventHPE · MMHPSDPA-MPJPE (mm): 47.36 -> 43.90Improved
add flow coherence loss on top of flow input (ablation)EventHPE · MMHPSDPVE (mm): 56.58 -> 53.90Improved
use geodesic SO(3) distance instead of Euclidean for pose loss (ablation)EventHPE · MMHPSDPA-MPJPE (mm): 49.02 -> 43.90Improved
use geodesic SO(3) distance instead of Euclidean for pose loss (ablation)EventHPE · MMHPSDPVE (mm): 59.84 -> 53.90Improved
add 3D and 2D joint supervision (ablation)EventHPE · MMHPSDPA-MPJPE (mm): 44.59 -> 43.90Improved
add 3D and 2D joint supervision (ablation)EventHPE · MMHPSDMPJPE (mm): 73.79 -> 71.79Improved

Later papers that compared with this method

2 later accepted papers report EventHPE as a baseline in their results tables; 2 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