AI Paper Atlas

Research map / 3D vision / 3D generation

HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observations

Sadegh Aliakbarian, Fatemeh Saleh, David Collier, Pashmina Cameron, Darren Cosker

ICCV 2023 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 23 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
replace learned and fixed mask parameters with temporally adaptable mask tokens (TAMT) (ablation)HMD-NeMo · AMASS hand trackingMPJPE / MPJVE: 5.59 -> 2.48 MPJPE; 42.81 -> 31.30 MPJVEImproved
add hands expressed in head space to the input (ablation)HMD-NeMo · AMASS hand trackingMPJPE: 4.38 -> 3.21Improved
add velocity inputs (ablation)HMD-NeMo · AMASS hand trackingMPJVE: 39.63 -> 35.27Improved
include GRU in the spatio-temporal encoder (ablation)HMD-NeMo · AMASS hand trackingMPJVE: 46.61 -> 31.30Improved
include transformer encoder in the spatio-temporal encoder (ablation)HMD-NeMo · AMASS hand trackingMPJPE: 5.55 -> 2.48Improved
add post-hoc optimization of predicted pose to observations (ablation)HMD-NeMo · AMASS motion controllersMPJPE: 2.07 -> 1.90 (MPJVE 26.07 -> 24.99)Improved
optimize with non-robust L2 energy in hand tracking (ablation)HMD-NeMo · AMASS hand trackingMPJPE / MPJVE: MPJPE 2.48 -> 2.32; MPJVE 31.30 -> 33.51Mixed
optimize with robust energy in hand tracking (ablation)HMD-NeMo · AMASS hand trackingMPJPE / MPJVE: MPJPE 2.48 -> 2.37; MPJVE 31.30 -> 31.33Mixed
add L_SE(3) loss on world-space joint transforms (ablation)HMD-NeMo · AMASSMPJPE / MPJVEImproved
add smoothness loss (ablation)HMD-NeMo · AMASSMPJVEImproved
add forecasting auxiliary loss for hands (ablation)HMD-NeMo · AMASSMPJPE / MPJVEImproved

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