Text to Figure文生图poster

SUE Spatial Uncertainty for Visual Place Recognition

This poster introduces Spatial Uncertainty Estimation (SUE), a method that fits a Gaussian to the poses of top-K retrieved images to estimate uncertainty in Visual Place Recognition (VPR), demonstrating superior efficiency and accuracy compared to methods like DUE and GV.

论文上下文

Paper title: On the Estimation of Image-matching Uncertainty in Visual Place Recognition Abstract: This poster introduces Spatial Uncertainty Estimation (SUE), a method that fits a Gaussian to the poses of top-K retrieved images to estimate uncertainty in Visual Place Recognition (VPR), demonstrating superior efficiency and accuracy compared to methods like DUE and GV. Paper body (method & results): <!DOCTYPE html> <html lang="en"> <head> <meta content="text/html; charset=utf-8" http-equiv="content-type"/> <title>On the Estimation of Image-matching Uncertainty in Visual Place Recognition</title> <!--Generated on Thu May 2 19:34:42 2024 by LaTeXML (version 0.8.8) 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.0.7.9.min.css" rel="stylesheet" type="text/css"/> <link href="/static/browse/0.3.4/css/ar5iv-fonts.0.7.9.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_new.js"></script> <script src="/static/browse/0.3.4/js/feedbackOverlay.js"></script> <base href="/html/2404.00546v1/"/></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/2404.00546v1#S1" title="In On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><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/2404.00546v1#S2" title="In On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><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/2404.00546v1#S3" title="In On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3 </span>Methodology</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/2404.00546v1#S3.SS1" title="In 3 Methodology ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.1 </span>Uncertainty estimation in VPR</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S3.SS2" title="In 3 Methodology ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.2 </span>Formalizing VPR</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S3.SS3" title="In 3 Methodology ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.3 </span>Current VPR uncertainty estimation categories</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S3.SS4" title="In 3 Methodology ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.4 </span>Spatial uncertainty estimation (<span class="ltx_text ltx_font_bold ltx_font_italic">SUE</span>) for VPR</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S3.SS5" title="In 3 Methodology ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">3.5 </span>Complementing geometric verification</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S4" title="In On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><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/2404.00546v1#S4.SS1" title="In 4 Experiments ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><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/2404.00546v1#S4.SS2" title="In 4 Experiments ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.2 </span>Performance comparison</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S4.SS3" title="In 4 Experiments ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.3 </span>Complementing geometric verification</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S4.SS4" title="In 4 Experiments ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.4 </span>Ablation study</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S4.SS5" title="In 4 Experiments ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">4.5 </span>Discussion</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S5" title="In On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">5 </span>Conclusions</span></a></li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S6" title="In On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">6 </span>Supplementary Material</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/2404.00546v1#S6.SS1" title="In 6 Supplementary Material ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">6.1 </span>More ablation studies of SUE</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S6.SS2" title="In 6 Supplementary Material ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">6.2 </span>A probabilistic view of SUE</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S6.SS3" title="In 6 Supplementary Material ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">6.3 </span>Spatial density compensation for dissimilar query/reference spatial distributions</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"> <a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S6.SS4" title="In 6 Supplementary Material ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">6.4 </span>Validating spatial density compensation</span></a> <ol class="ltx_toclist ltx_toclist_subsection"> <li class="ltx_tocentry ltx_tocentry_paragraph"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S6.SS4.SSS0.Px1" title="In 6.4 Validating spatial density compensation ‣ 6 Supplementary Material ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title">Applying a uniform spatial prior for the query</span></a></li> <li class="ltx_tocentry ltx_tocentry_paragraph"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S6.SS4.SSS0.Px2" title="In 6.4 Validating spatial density compensation ‣ 6 Supplementary Material ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title">Do common datasets have a uniform query distribution?</span></a></li> <li class="ltx_tocentry ltx_tocentry_paragraph"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S6.SS4.SSS0.Px3" title="In 6.4 Validating spatial density compensation ‣ 6 Supplementary Material ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title">Does assuming a uniform query distribution help?</span></a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S6.SS5" title="In 6 Supplementary Material ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">6.5 </span>Precision-Recall curves</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S6.SS6" title="In 6 Supplementary Material ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">6.6 </span>Complementing geometric verification</span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S6.SS7" title="In 6 Supplementary Material ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">6.7 </span><span class="ltx_text ltx_font_bold" style="color:#000000;">SUE combined with other uncertainty estimates</span></span></a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2404.00546v1#S6.SS8" title="In 6 Supplementary Material ‣ On the Estimation of Image-matching Uncertainty in Visual Place Recognition"><span class="ltx_text ltx_ref_title"><span class="ltx_tag ltx_tag_ref">6.8 </span>Relating SUE to geometri

完整 Prompt

Above I've shared:
(1) the full paper text,
(2) all paper figures labeled by figure number,
(3) the caption for the central poster figure I'm building.

TASK: This is a CONFERENCE POSTER. **NOT** an academic-paper figure.
Style requirements:

  - Multi-section layout with a clear poster structure: large title banner
    at the top with the paper title + author/affiliation strip, then 3-6
    distinct content panels arranged in columns or a grid.
  - Large legible fonts (text must be readable at 2 m viewing distance) —
    headings ≥ 60 pt visual size in the final image.
  - Use colour blocks / panel backgrounds to delineate sections (this is
    what makes it a poster, not a single-figure diagram).
  - Aspect ratio: portrait or landscape rectangle, NOT square.

If your output looks like a standard academic-paper figure (single panel,
no title banner, dense small text, no colour blocks), you've failed the
task. Render the COMPLETE poster, not just the central figure.

Just give me the final poster image.

立即试用此 Prompt

在生成器中自动预填此 prompt。

试用此 Prompt

相关 Prompt