Weakly‐Supervised Dynamic Point Cloud Saliency Prediction Network
Computer Animation and Virtual Worlds · 2026-05 · 37 (3)
DOI: 10.1002/cav.70157 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Animation and Virtual Worlds, online erschienen am 19.06.2026. Verfasst von Hongyang Lv und 3 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben.
Abstract (Originalsprache)
Point cloud saliency prediction, which models Human Visual System (HVS) attention, is essential for applications like Computer Animation and eXtended Reality (XR). However, most existing research focuses on static scenes, and extending these models to dynamic point clouds is hindered by motion‐induced attention shifts and a lack of ground‐truth dynamic datasets. To address this, we propose the Weakly‐Supervised Dynamic Point Cloud Saliency Prediction Network (WDPS), one of the first frameworks to utilize classification supervision for dynamic 3D saliency. WDPS integrates saliency‐oriented feature mining, multiscale semantic‐detail fusion, and a temporal smoothness constraint to generate stable dynamic saliency maps. Extensive experiments demonstrate that our method is preferred by observers in over 78% of comparisons against static baselines. Furthermore, WDPS achieves superior Velocity‐Weighted Saliency (VWS) scores on highly dynamic sequences and significantly enhances downstream tasks performance.
Zitieren
APA
Lv, H., Yang, B., Nan, F., & Jiang, Z. (2026). Weakly‐Supervised Dynamic Point Cloud Saliency Prediction Network. Computer Animation and Virtual Worlds, 37(3). https://doi.org/10.1002/cav.70157
Vancouver
Lv H, Yang B, Nan F, Jiang Z. Weakly‐Supervised Dynamic Point Cloud Saliency Prediction Network. Computer Animation and Virtual Worlds. 2026;37(3). doi:10.1002/cav.70157
BibTeX
@article{Lv2026,
author = {Lv, Hongyang and Yang, Bailin and Nan, Fangzhe and Jiang, Zhaoyi},
title = {Weakly‐Supervised Dynamic Point Cloud Saliency Prediction Network},
journal = {Computer Animation and Virtual Worlds},
year = {2026},
volume = {37},
number = {3},
doi = {10.1002/cav.70157}
}
EUVIMED