AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Learning Parallel Dense Correspondence From Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction

Jiapeng Tang, Dan Xu, Kui Jia, Lei Zhang

CVPR 2021 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 27 citations (OpenAlex)

Check 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 LPDC-Net instead of OFlow4D reconstruction · D-FAUST, time-evenly sampled, S1IoU: 81.5% -> 84.9%Improved
use LPDC-Net instead of OFlow4D reconstruction · D-FAUST, time-evenly sampled, S1Chamfer distance: 0.065 -> 0.055Improved
use LPDC-Net instead of OFlow4D reconstruction · D-FAUST, time-unevenly sampled, S1IoU: 76.9% -> 83.8%Improved
use LPDC-Net instead of OFlow4D reconstruction · D-FAUST, time-unevenly sampled, S2Correspondence distance: 0.178 -> 0.118Improved
use parallel occupancy-field transformations rather than OFlow's sequential ODE-based motion modeling4D reconstruction inference · D-FAUST test sequencesInference time (s): 1.84 -> 0.23Improved
add the proposed spatio-temporal encoder (ablation)LPDC-Net 4D shape completion · D-FAUST, time-unevenly sampled, S1IoU: 81.0% -> 82.4%Improved
add the proposed spatio-temporal encoder (ablation)LPDC-Net 4D shape completion · D-FAUST, time-unevenly sampled, S2IoU: 71.7% -> 72.9%Improved
use parallel correspondence modeling rather than sequential adjacent-frame transformations (ablation)LPDC-Net 4D shape completion · D-FAUST, time-unevenly sampled, S1Correspondence distance: 0.254 -> 0.105Improved
use parallel correspondence modeling rather than sequential adjacent-frame transformations (ablation)LPDC-Net 4D shape completion · D-FAUST, time-unevenly sampled, S2Correspondence distance: 0.344 -> 0.134Improved

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