AI Paper Atlas

Research map / Point clouds / Point cloud classification

PUMPS: Skeleton-Agnostic Point-based Universal Motion Pre-Training for Synthesis in Human Motion Tasks

Clinton Ansun Mo, Kun Hu, Chengjiang Long, Dong Yuan, Wan-Chi Siu, Zhiyong Wang

ICCV 2025 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 1 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
use sequence-wise dropout instead of element-wise dropout in the TPC decoder (ablation)PUMPS auto-encoder · TPC reconstructionL_rec: 0.0204 -> 0.0029Improved
use rotary self-attention instead of sinusoidal positions (ablation)PUMPS auto-encoder · TPC reconstructionL_rec: 0.0052 -> 0.0029Improved
use linear assignment (Hungarian) pairing instead of Chamfer distance objective (ablation)PUMPS auto-encoder · TPC reconstructionL_rec: 0.0085 -> 0.0029Improved
use Gaussian-noise point identifiers instead of FoldingNet 2D folding (ablation)PUMPS auto-encoder · TPC reconstructionL_rec: 0.0040 -> 0.0029Improved
use Gaussian-noise point identifiers instead of PointIVAE VAE sampling (ablation)PUMPS auto-encoder · TPC reconstructionL_rec: 0.0260 -> 0.0029Improved
pre-train on TPC motion completion before fine-tuning for 2D-to-3D estimation (ablation)PUMPS latent motion synthesiser · 2D-to-3D motion estimationMPJPE: 73.56 -> 44.15 (Aim)Improved
pre-train on TPC motion completion before fine-tuning for denoising (ablation)PUMPS latent motion synthesiser · Motion denoising (LaFAN1)MPJPE: 70.20 -> 49.83 (Aim)Improved
pre-train before fine-tuning for denoising, acceleration error (ablation)PUMPS latent motion synthesiser · Motion denoising (LaFAN1)Acceleration error: 8.92 -> 10.45 (Aim)Hurt
interpolate in the PUMPS point cloud latent space rather than skeletal spacePUMPS · Keyframe interpolation and motion transitionL2P: 0.137 vs 0.186 (5-frame, CITL); 0.948 vs 0.908 (30-frame)Mixed
PUMPS vs MHFormer on 2D-to-3D estimationPUMPS (finetune) · 2D-to-3D motion estimationMPJPE: 44.15 vs 40.38 (Aim)Mixed

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