English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper focuses on the task of 4D shape reconstruction from a sequence ofpoint clouds. Despite the recent success achieved by extending deep implicitrepresentations into 4D space, it is still a great challenge in two respects,i.e. how to design a flexible framework for learning robust spatio-temporalshape representations from 4D point clouds, and develop an efficient mechanismfor capturing shape dynamics. In this work, we present a novel pipeline tolearn a temporal evolution of the 3D human shape through spatially continuoustransformation functions among cross-frame occupancy fields. The key idea is toparallelly establish the dense correspondence between predicted occupancyfields at different time steps via explicitly learning continuous displacementvector fields from robust spatio-temporal shape representations. Extensivecomparisons against previous state-of-the-arts show the superior accuracy ofour approach for 4D human reconstruction in the problems of 4D shapeauto-encoding and completion, and a much faster network inference with about 8times speedup demonstrates the significant efficiency of our approach. Thetrained models and implementation code are available athttps://github.com/tangjiapeng/LPDC-Net.

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