VPSeg Vanishing-Point Video Segmentation — Poster
A CVPR 2024 poster presenting VPSeg, a network utilizing vanishing points for video semantic segmentation. It details the MotionVP and DenseVP modules, quantitative comparisons on ACDC/Cityscapes, and qualitative segmentation results.
Paper context
Paper title: Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes Abstract: A CVPR 2024 poster presenting VPSeg, a network utilizing vanishing points for video semantic segmentation. It details the MotionVP and DenseVP modules, quantitative comparisons on ACDC/Cityscapes, and qualitative segmentation results. Paper body (method & results): <!DOCTYPE html> <html lang="en"> <head> <meta content="text/html; charset=utf-8" http-equiv="content-type"/> <title>Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes</title> <!--Generated on Sat Jan 27 00:53:44 2024 by LaTeXML (version 0.8.7) http://dlmf.nist.gov/LaTeXML/.--> <meta content="width=device-width, initial-scale=1, shrink-to-fit=no" name="viewport"/> <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css" rel="stylesheet" type="text/css"/> <link href="/static/browse/0.3.4/css/ar5iv_0.7.4.min.css" rel="stylesheet" type="text/css"/> <link href="/static/browse/0.3.4/css/latexml_styles.css" rel="stylesheet" type="text/css"/> <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/js/bootstrap.bundle.min.js"></script> <script src="https://cdnjs.cloudflare.com/ajax/libs/html2canvas/1.3.3/html2canvas.min.js"></script> <script src="/static/browse/0.3.4/js/addons.js"></script> <script src="/static/browse/0.3.4/js/feedbackOverlay.js"></script> <base href="/html/2401.15261v1/"/></head> <body> <nav class="ltx_page_navbar"> <nav class="ltx_TOC"> <ol class="ltx_toclist"> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S1" title="1 Introduction ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">1 </span>Introduction</span></a></li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S2" title="2 Related Work ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">2 </span>Related Work</span></a> <ol class="ltx_toclist ltx_toclist_section"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S2.SS1" title="2.1 Efficient VSS ‣ 2 Related Work ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">2.1 </span>Efficient VSS</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S2.SS2" title="2.2 High-Performance VSS ‣ 2 Related Work ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">2.2 </span>High-Performance VSS</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S2.SS3" title="2.3 VP Detection ‣ 2 Related Work ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">2.3 </span>VP Detection</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S3" title="3 VPSeg: VP-Guided Network for VSS ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3 </span>VPSeg: VP-Guided Network for VSS</span></a> <ol class="ltx_toclist ltx_toclist_section"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S3.SS1" title="3.1 MotionVP: VP-Guided Motion Fusion ‣ 3 VPSeg: VP-Guided Network for VSS ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.1 </span>MotionVP: VP-Guided Motion Fusion</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S3.SS2" title="3.2 DenseVP: Sparse-to-Dense Feature Mining ‣ 3 VPSeg: VP-Guided Network for VSS ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.2 </span>DenseVP: Sparse-to-Dense Feature Mining</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S3.SS3" title="3.3 CMA: Contextualized Motion Attention ‣ 3 VPSeg: VP-Guided Network for VSS ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.3 </span>CMA: Contextualized Motion Attention</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S4" title="4 Experiments ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4 </span>Experiments</span></a> <ol class="ltx_toclist ltx_toclist_section"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S4.SS1" title="4.1 Experimental Setup ‣ 4 Experiments ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.1 </span>Experimental Setup</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S4.SS2" title="4.2 Comparison with the State of the Art ‣ 4 Experiments ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.2 </span>Comparison with the State of the Art</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S4.SS3" title="4.3 Ablation Studies ‣ 4 Experiments ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.3 </span>Ablation Studies</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S5" title="5 Conclusion ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">5 </span>Conclusion</span></a></li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#S6" title="6 Acknowledgments ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">6 </span>Acknowledgments</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#A1" title="Appendix A Vanishing Point Detection ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">A </span>Vanishing Point Detection</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#A2" title="Appendix B Additional Ablation Studies ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">B </span>Additional Ablation Studies</span></a></li> <li class="ltx_tocentry ltx_tocentry_appendix"><a class="ltx_ref" href="https://arxiv.org/html/2401.15261v1#A3" title="Appendix C Detailed Pipelines ‣ Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">C </span>Detailed Pipelines</span></a></li> </ol></nav> </nav> <div class="ltx_page_main"> <div class="ltx_page_content"> <div aria-label="Conversion errors have been found" class="package-alerts ltx_document" role="status"> <button aria-label="Dismiss alert" onclick="closePopup()"> <span aria-hidden="true"><svg aria-hidden="true" focusable="false" height="20" role="presentation" viewbox="0 0 44 44" width="20"> <path d="M0.549989 4.44999L4.44999 0.549988L43.45 39.55L39.55 43.45L0.549989 4.44999Z"></path> <path d="M39.55 0.549988L43.45 4.44999L4.44999 43.45L0.549988 39.55L39.55 0.549988Z"></path> </svg></span> </button> <p>HTML conversions <a href="https://info.dev.arxiv.org/about/accessibility_html_error_messages.html" target="_blank">sometimes display errors</a> due to content that did not convert correctly from the source. This paper uses the following packages that are not yet supported by the HTML conversion tool. Feedback on these issues are not necessary; they are known and are being worked on.</p> <ul arial-label="Unsupported packages used in this paper"> <li>failed: epic</li> <li>failed: contour</li> <li>failed: epic</li> </ul> <p>Authors: achieve the best HTML results from your LaTeX submissions by following these <a href="https://info.arxiv.org/help/submit_latex_best_practices.html" target="_blank">best practices</a>.</p> </div><div class="section" id="target-section"><div id="license-tr">License: arXiv.org perpetual non-exclusive license</div><div id="watermark-tr">arXiv:2401.15261v1 [cs.CV] 27 Jan 2024</div></div> <script> function closePopup() { document.querySelector('.package-alerts').style.display = 'none'; } </script> <article class="ltx_document ltx_authors_1line"> <h1 class="ltx_title ltx_title_document">Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes</h1> <div class="ltx_authors"> <span class="ltx_creator ltx_role_author"> <span class="ltx_personname"> Diandian Guo<math alttext="{}^{1}" class="ltx_Math" display="inline" id="id1.1.m1.1"><semantics id="id1.1.m1.1a"><msup id="id1.1.m1.1.1" xref="id1.1.m1.1.1.cmml"><mi id="id1.1.m1.1.1a" xref="id1.1.m1.1.1.cmml"></mi><mn id="id1.1.m1.1.1.1" xref="id1.1.m1.1.1.1.cmml">1</mn></msup><annotation-xml encoding="MathML-Content" id="id1.1.m1.1b"><apply id="id1.1.m1.1.1.cmml" xref="id1.1.m1.1.1"><cn id="id1.1.m1.1.1.1.cmml" type="integer" xref="id1.1.m1.1.1.1">1</cn></apply></annotation-xml><annotation encoding="application/x-tex" id="id1.1.m1.1c">{}^{1}</annotation><annotation encoding="application/x-llamapun" id="id1.1.m1.1d">start_FLOATSUPERSCRIPT 1 end_FLOATSUPERSCRIPT</annotation></semantics></math> Deng-Ping Fan<math alttext="{}^{2,1}" class="ltx_Math" display="inline" id="id2.2.m2.2"><semantics id="id2.2.m2.2a"><msup id="id2.2.m2.2.2" xref="id2.2.m2.2.2.cmml"><mi id="id2.2.m2.2.2a" xref="id2.2.m2.2.2.cmml"></mi><mrow id="id2.2.m2.2.2.2.4" xref="id2.2.m2.2.2.2.3.cmml"><mn id="id2.2.m2.1.1.1.1" xref="id2.2.m2.1.1.1.1.cmml">2</mn><mo id="id2.2.m2.2.2.2.4.1" xref="id2.2.m2.2.2.2.3.cmml">,</mo><mn id="id2.2.m2.2.2.2.2" xref="id2.2.m2.2.2.2.2.cmml">1</mn></mrow></msup><annotation-xml encoding="MathML-Content" id="id2.2.m2.2b"><apply id="id2.2.m2.2.2.cmml" xref="id2.2.m2.2.2"><list id="id2.2.m2.2.2.2.3.cmml" xref="id2.2.m2.2.2.2.4"><cn id="id2.2.m2.1.1.1.1.cmml" type="integer" xref="id2.2.m2.1.1.1.1">2</cn><cn id="id2.2.m2.2.2.
