AI Paper Atlas

Research map / 3D vision / Human pose estimation

Predicting 3D Human Dynamics From Video

Jason Y. Zhang, Panna Felsen, Angjoo Kanazawa, Jitendra Malik

ICCV 2019 · 3D vision › Human pose estimation · approach: Human motion prediction · 97 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
predict in the latent movie-strip space instead of 3D mesh space (ablation)autoregressive predictor · Human3.6M, 30 frames (DTW)reconstruction error (mm): 82.6 -> 65.1Improved
predict in the latent space instead of mesh space (ablation)autoregressive predictor · Penn Action, 30 frames (DTW)PCK: 56.5 -> 77.2Improved
predict in the latent space instead of mesh space (ablation)autoregressive predictor · Human3.6M, 30 frames (no DTW)reconstruction error (mm): 105.2 -> 81.1Improved
predict in the latent space instead of mesh space (ablation)autoregressive predictor · Penn Action, 30 frames (no DTW)PCK: 35.1 -> 60.1Improved
add the movie-strip distillation loss (ablation)AR on latent Phi · Penn Action, 30 frames (DTW)PCK: 75.6 -> 77.2Improved
add the movie-strip distillation loss (ablation)AR on latent Phi · Human3.6M, 30 frames (DTW)reconstruction error (mm): 65.3 -> 65.1No clear effect
autoregressive latent prediction instead of constant no-motion baselineAR on latent Phi · Human3.6M, 30 frames (DTW)reconstruction error (mm): 90.4 -> 65.1Improved
autoregressive latent prediction instead of nearest neighbor baselineAR on latent Phi · Penn Action, 30 frames (DTW)PCK: 57.8 -> 77.2Improved
use a causal temporal encoder without future frames instead of the bidirectional onetemporal encoder · Human3.6MMPJPE (mm): 83.7 -> 83.9No clear effect
use the causal encodertemporal encoder · Penn ActionPCK: 79.6 -> 80.6No clear effect
condition on a sequence of past frames in autoregressive prediction instead of a single imagefuture predictor · Penn Action, 5 frames aheadPCK: 68.1 -> 77.2Improved

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