UniMODE Unified Monocular 3D Detection — Poster
A conference poster for UniMODE, a unified monocular 3D object detection method. It features a framework diagram, motivation panels showing indoor/outdoor scenes, training stability graphs, and quantitative results tables.
Paper context
Paper title: UniMODE: Unified Monocular 3D Object Detection Abstract: A conference poster for UniMODE, a unified monocular 3D object detection method. It features a framework diagram, motivation panels showing indoor/outdoor scenes, training stability graphs, and quantitative results tables. Paper body (method & results): <!DOCTYPE html> <html lang="en"> <head> <meta content="text/html; charset=utf-8" http-equiv="content-type"/> <title>UniMODE: Unified Monocular 3D Object Detection</title> <!--Generated on Tue Feb 27 09:24:24 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/2402.18573v1/"/></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/2402.18573v1#S1" title="1 Introduction ‣ UniMODE: Unified Monocular 3D Object Detection"><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/2402.18573v1#S2" title="2 Related Work ‣ UniMODE: Unified Monocular 3D Object Detection"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">2 </span>Related Work</span></a></li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2402.18573v1#S3" title="3 Method ‣ UniMODE: Unified Monocular 3D Object Detection"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3 </span>Method</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/2402.18573v1#S3.SS1" title="3.1 Overall Framework ‣ 3 Method ‣ UniMODE: Unified Monocular 3D Object Detection"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.1 </span>Overall Framework</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2402.18573v1#S3.SS2" title="3.2 Two-Stage Detection Architecture ‣ 3 Method ‣ UniMODE: Unified Monocular 3D Object Detection"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.2 </span>Two-Stage Detection Architecture</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2402.18573v1#S3.SS3" title="3.3 Uneven BEV Grid ‣ 3 Method ‣ UniMODE: Unified Monocular 3D Object Detection"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.3 </span>Uneven BEV Grid</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2402.18573v1#S3.SS4" title="3.4 Sparse BEV Feature Projection ‣ 3 Method ‣ UniMODE: Unified Monocular 3D Object Detection"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.4 </span>Sparse BEV Feature Projection</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2402.18573v1#S3.SS5" title="3.5 Unified Domain Alignment ‣ 3 Method ‣ UniMODE: Unified Monocular 3D Object Detection"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.5 </span>Unified Domain Alignment</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2402.18573v1#S4" title="4 Experiment ‣ UniMODE: Unified Monocular 3D Object Detection"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4 </span>Experiment</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/2402.18573v1#S4.SS1" title="4.1 Performance Comparison ‣ 4 Experiment ‣ UniMODE: Unified Monocular 3D Object Detection"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.1 </span>Performance Comparison</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2402.18573v1#S4.SS2" title="4.2 Ablation Studies ‣ 4 Experiment ‣ UniMODE: Unified Monocular 3D Object Detection"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.2 </span>Ablation Studies</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2402.18573v1#S4.SS3" title="4.3 Cross-domain Evaluation ‣ 4 Experiment ‣ UniMODE: Unified Monocular 3D Object Detection"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.3 </span>Cross-domain Evaluation</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2402.18573v1#S4.SS4" title="4.4 Visualization ‣ 4 Experiment ‣ UniMODE: Unified Monocular 3D Object Detection"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.4 </span>Visualization</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2402.18573v1#S5" title="5 Conclusion and Limitation ‣ UniMODE: Unified Monocular 3D Object Detection"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">5 </span>Conclusion and Limitation</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: utfsym</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:2402.18573v1 [cs.CV] 28 Feb 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">UniMODE: Unified Monocular 3D Object Detection</h1> <div class="ltx_authors"> <span class="ltx_creator ltx_role_author"> <span class="ltx_personname">Zhuoling Li<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>, Xiaogang Xu<math alttext="{}^{2}" class="ltx_Math" display="inline" id="id2.2.m2.1"><semantics id="id2.2.m2.1a"><msup id="id2.2.m2.1.1" xref="id2.2.m2.1.1.cmml"><mi id="id2.2.m2.1.1a" xref="id2.2.m2.1.1.cmml"></mi><mn id="id2.2.m2.1.1.1" xref="id2.2.m2.1.1.1.cmml">2</mn></msup><annotation-xml encoding="MathML-Content" id="id2.2.m2.1b"><apply id="id2.2.m2.1.1.cmml" xref="id2.2.m2.1.1"><cn id="id2.2.m2.1.1.1.cmml" type="integer" xref="id2.2.m2.1.1.1">2</cn></apply></annotation-xml><annotation encoding="application/x-tex" id="id2.2.m2.1c">{}^{2}</annotation><annotation encoding="application/x-llamapun" id="id2.2.m2.1d">start_FLOATSUPERSCRIPT 2 end_FLOATSUPERSCRIPT</annotation></semantics></math>, SerNam Lim<math alttext="{}^{3}" class="ltx_Math" display="inline" id="id3.3.m3.1"><semantics id="id3.3.m3.1a"><msup id="id3.3.m3.1.1" xref="id3.3.m3.1.1.cmml"><mi id="id3.3.m3.1.1a" xref="id3.3.m3.1.1.cmml"></mi><mn id="id3.3.m3.1.1.1" xref="id3.3.m3.1.1.1.cmml">3</mn></msup><annotation-xml encoding="MathML-Content" id="id3.3.m3.1b"><apply id="id3.3.m3.1.1.cmml" xref="id3.3.m3.1.1"><cn id="id3.3.m3.1.1.1.cmml" type="integer" xref="id3.3.m3.1.1.1">3</cn></apply></annotation-xml><annotation encoding="application/x-tex" id="id3.3.m3.1c">{}^{3}</annotation><annotation encoding="application/x-llamapun" id="id3.3.m3.1d">start_FLOATSUPERSCRIPT 3 end_FLOATSUPERSCRIPT</annotation></semantics></math>, Hengshuang Zhao<math alttext="{}^{1}" class="ltx_Math" display="inline" id="id4.4.m4.1"><semantics id="id4.4.m4.1a"><msup id="id4.4.m4.1.1" xref="id4.4.m4.1.1.cmml"><mi id="id4.4.m4.1.1a" xref="id4.4.m4.1.1.cmml"></mi><mn id="id4.4.m4.1.1.1" xref="id4.4.m4.1.1.1.cmml">1</mn></msup><annotation-xml encoding="MathML-Content" id="id4.4.m4.1b"><apply id="id4.4.m4.1.1.cmml" xref="id4.4.m4.1.1"><cn id="id4.4.m4.1.1.1.cmml" type="integer" xref="id4.4.m4.1.1.1">1</cn></apply></annotation-xml><annotation encoding="application/x-tex" id="id4.4.m4.1c">{}^{1}</annotation><annotation encoding="application/x-llamapun" id="id4.4.m4.1d">start_FLOATSUPERSCRIPT 1 end_FLOATSUPERSCRIPT</annotation></semantics></math> <br class="ltx_break"/><math alttext="{}^{1}" class="ltx_Math" display="inline" id="id5.5.m5.1"><semantics id="id5.5.m5.1a"><msup id="id5.5.m5.1.1" xref="id5.5.m5.1.1.cmml"><mi id="id5.5.m5.1.1a" xref="id5.5.m5.1.1.cmml"></mi><mn id="id5.5.m5.1.1.1" xref="id5.5.m5.1.1.1.cmml">1</mn></msup><annotation-xml encoding="MathML-Content" id="id5.5.m5.1b"><apply id="id5.5.m5.1.1.cmml" xref="id5.5.m5.1.1"><cn id="id5.5.m5.1.1.1.cmml" type="integer" xref="id5.5.m5.1.1.1">1</cn></apply></annotation-xml><annotation encoding="application/x-tex" id="id5.5.m5.1c">{}^{1}</annotation><annotation encoding="app
