Skip to content

Latest commit

 

History

History
47 lines (37 loc) · 2.45 KB

README.md

File metadata and controls

47 lines (37 loc) · 2.45 KB

Deflickering Vision-Based Occupancy Networks through Lightweight Spatio-Temporal Correlation

Fengcheng Yu1*, Haoran Xu1,2*, Canming Xia1,2, Ziyang Zong1, Guang Tan1†

1Sun Yat-sen University   ·   2Peng Cheng Laboratory

* Equal contribution.    † Corresponding author.

Vision-based occupancy networks (VONs) provide an end-to-end solution for reconstructing 3D environments in autonomous driving. However, existing methods often suffer from temporal inconsistencies, manifesting as flickering effects that compromise visual experience and adversely affect decision-making. While recent approaches have incorporated historical data to mitigate the issue, they often incur high computational costs and may introduce noisy information that interferes with object detection. We propose OccLinker, a novel plugin framework designed to seamlessly integrate with existing VONs for boosting performance. Our method efficiently consolidates historical static and motion cues, learns sparse latent correlations with current features through a dual cross-attention mechanism, and produces correction occupancy components to refine the base network’s predictions. We propose a new temporal consistency metric to quantitatively identify flickering effects. Extensive experiments on two benchmark datasets demonstrate that our method delivers superior performance with negligible computational overhead, while effectively eliminating flickering artifacts.

Paper: Pattern Recognition    arXiv: 2502.15438    Project page: ffengc.github.io/occlinker

Code coming soon.

News & Updates

  • [2026-09-27] Published online in Pattern Recognition.
  • [2026-09-12] Accepted by Pattern Recognition.
  • [2025-02-21] Paper released on arXiv.

Citation

@article{yu2027occlinker,
  title   = {Deflickering Vision-Based Occupancy Networks through Lightweight
             Spatio-Temporal Correlation},
  author  = {Yu, Fengcheng and Xu, Haoran and Xia, Canming
             and Zong, Ziyang and Tan, Guang},
  journal = {Pattern Recognition},
  volume  = {183},
  pages   = {114988},
  year    = {2027},
  doi     = {10.1016/j.patcog.2026.114988}
}