AI Paper Atlas

Research map / 3D vision / Human pose estimation

SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos

Ailing Zeng, Lei Yang, Xuan Ju, Jiefeng Li, Jianyi Wang, Qiang Xu

ECCV 2022 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 118 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 acceleration loss to the backbone training (ablation)VPose In=27 · Human3.6MAccel / MPJPE: Accel 5.07 -> 4.12; MPJPE 50.13 -> 51.48Mixed
train SmoothNet end-to-end with the backbone instead of two-stage (ablation)VPose In=27 · Human3.6MMPJPE (mm): 50.04 -> 52.65Hurt
train SmoothNet separately (two-stage) after the backbone (ablation)VIBE In=16 · 3DPWMPJPE (mm): 86.56 -> 81.42Improved
add intermediate L1 supervision and acceleration loss to end-to-end SmoothNet (ablation)VPose In=27 w/ B · Human3.6MAccel / MPJPE: Accel 5.46 -> 2.69; MPJPE 51.06 -> 50.94Improved
add SmoothNet to single-frame backboneVIBE In=1 · 3DPWAccel: 32.69 -> 6.12Improved
use SmoothNet instead of filters with similar AccelFCN · Human3.6M 3D poseMPJPE (mm): 143.24 -> 52.72Improved
use SmoothNet instead of best filterTPoseNet · MuPoTS-3DAccel: 8.29 -> 7.23Improved
add SmoothNet on top of RefineNetTPoseNet w/ RefineNet · MuPoTS-3DMPJPE (mm): 93.97 -> 91.78Improved
add acceleration loss to pose loss (ablation)SmoothNet · 3DPW (EFT)Accel: 6.42 -> 6.30Improved
add pose loss to acceleration-only training (ablation)SmoothNet · 3DPW (EFT)MPJPE (mm): 446.54 -> 86.39Improved
use 3D position instead of axis-angle as training modality (ablation)SmoothNet · 3DPW (EFT)Accel: 77.89 -> 6.30Improved
use 3D position instead of 6D rotation as training modality (ablation)SmoothNet · 3DPW (EFT)MPJPE (mm): 86.92 -> 86.39Improved

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