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

[2502.15438] Deflickering Vision-Based Occupancy Networks through Lightweight Spatio-Temporal Correlation Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2502.15438 (cs) [Submitted on 21 Feb 2025 ( v1 ), last revised 28 Aug 2026 (this version, v5)] Title: Deflickering Vision-Based Occupancy Networks through Lightweight Spatio-Temporal Correlation Authors: Fengcheng Yu , Haoran Xu , Canming Xia , Ziyang Zong , Guang Tan View PDF HTML (experimental) Abstract: 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 degrade temporal coherence and adversely affect downstream decision-making. While recent approaches incorporate historical information to alleviate this issue, they often incur high computational costs and may introduce misaligned or redundant features that interfere with object detection. We propose OccLinker, a novel plugin framework that can be easily integrated into existing VONs to improve performance. Our method efficiently consolidates historical static and motion cues, learns sparse latent correlations with current features through a dual cross-attention mechanism, and generates correction occupancy components to refine the base network predictions. In addition, we introduce a new temporal consistency metric to quantitatively measure flickering effects. Extensive experiments on two benchmark datasets demonstrate that our method achieves superior performance with minimal computational overhead while effectively reducing flickering artifacts. Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2502.15438 [cs.CV] (or arXiv:2502.15438v5 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2502.15438 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Fengcheng Yu [ view email ] [v1] Fri, 21 Feb 2025 13:07:45 UTC (35,503 KB) [v2] Mon, 10 Mar 2025 13:57:27 UTC (5,085 KB) [v3] Mon, 14 Jul 2025 06:03:23 UTC (4,532 KB) [v4] Tue, 6 Jan 2026 23:08:11 UTC (8,329 KB) [v5] Fri, 28 Aug 2026 00:07:17 UTC (17,911 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CV < prev | next > new | recent | 2025-02 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Deflickering Vision-Based Occupancy Networks through Lightweight Spatio-Temporal Correlation#684207
• RoadOcc Learns When to Persist, Transport, or Refresh Memory for Roadside Occupancy Prediction#1064221
• DiDA: Video Object Segmentation with Distillation Learning of Deformable Attention#1144689
• Visual Pattern Completion of Occluded Objects Promotes Robust Visual Learning#313361
• Still Camouflage, Moving Illusion: View-Induced Trajectory Manipulation in Autonomous Driving#180608