AI Paper Atlas

Research map / Point clouds / Point cloud classification

Dynamic Mesh Recovery from Partial Point Cloud Sequence

Hojun Jang, Minkwan Kim, Jinseok Bae, Young Min Kim

ICCV 2023 · Point clouds › Point cloud classification · approach: Point cloud detection and tracking · 5 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 auxiliary pose loss to kinematics learner (ablation)Kinematics learner · AMASS subsetvertex error: 0.0309 -> 0.0215Improved
add volume fitting loss to kinematics learner (ablation)Kinematics learner · AMASS subsetvertex error: 0.1217 -> 0.0215Improved
pretrain kinematics prior then use feature follower instead of training directly on partial input (ablation)Feature follower pipeline · Synthetic human motionvertex error: 0.1018 -> 0.0132Improved
add feature following loss L_F (ablation)Feature follower · Synthetic human motionvertex error: 0.0166 -> 0.0132Improved
use full-capacity transformer in feature follower instead of quartered (ablation)Feature follower · Synthetic human motionvertex error: 0.0190 -> 0.0132Improved
sequence-level temporal modeling versus per-frame baselinesOurs vs VoteHMR · Synthetic human motionvertex error: 0.0258 -> 0.0132Improved
Ours vs optimization-based Zuo et al. on real dataOurs · Berkeley MHADChamfer distance: 0.0014 (Zuo) vs 0.0027 (Ours)Hurt

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