Text to FigureText → Imageposter

Urban Dynamic Scene 3D Gaussians — Poster

A conference poster presenting a method for dynamic scene representation in urban areas using 3D Gaussians and neural fields, addressing limitations of static 3D Gaussian Splatting.

Paper context

Paper title: Dynamic 3D Gaussian Fields for Urban Areas Abstract: A conference poster presenting a method for dynamic scene representation in urban areas using 3D Gaussians and neural fields, addressing limitations of static 3D Gaussian Splatting. Paper body (method & results): <!DOCTYPE html> <html lang="en"> <head> <meta content="text/html; charset=utf-8" http-equiv="content-type"/> <title>Dynamic 3D Gaussian Fields for Urban Areas</title>  <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/2406.03175v1/"/></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/2406.03175v1#S1" title="In Dynamic 3D Gaussian Fields for Urban Areas">1 Introduction</a></li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#S2" title="In Dynamic 3D Gaussian Fields for Urban Areas">2 Related Work</a></li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#S3" title="In Dynamic 3D Gaussian Fields for Urban Areas">3 Method</a> <ol class="ltx_toclist ltx_toclist_section"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#S3.SS1" title="In 3 Method ‣ Dynamic 3D Gaussian Fields for Urban Areas">3.1 Problem setup</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#S3.SS2" title="In 3 Method ‣ Dynamic 3D Gaussian Fields for Urban Areas">3.2 Representation</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#S3.SS3" title="In 3 Method ‣ Dynamic 3D Gaussian Fields for Urban Areas">3.3 Composition and Rendering</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#S3.SS4" title="In 3 Method ‣ Dynamic 3D Gaussian Fields for Urban Areas">3.4 Optimization</a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"> <a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#S4" title="In Dynamic 3D Gaussian Fields for Urban Areas">4 Experiments</a> <ol class="ltx_toclist ltx_toclist_section"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#S4.SS1" title="In 4 Experiments ‣ Dynamic 3D Gaussian Fields for Urban Areas">4.1 Comparison to State-of-the-Art</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#S4.SS2" title="In 4 Experiments ‣ Dynamic 3D Gaussian Fields for Urban Areas">4.2 Ablation Studies</a></li> </ol> </li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#S5" title="In Dynamic 3D Gaussian Fields for Urban Areas">5 Conclusion</a></li> <li class="ltx_tocentry ltx_tocentry_section"><a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#S6" title="In Dynamic 3D Gaussian Fields for Urban Areas">6 Acknowledgements</a></li> <li class="ltx_tocentry ltx_tocentry_appendix"> <a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#A1" title="In Dynamic 3D Gaussian Fields for Urban Areas">A Appendix</a> <ol class="ltx_toclist ltx_toclist_appendix"> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#A1.SS1" title="In Appendix A Appendix ‣ Dynamic 3D Gaussian Fields for Urban Areas">A.1 Demonstration Video</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#A1.SS2" title="In Appendix A Appendix ‣ Dynamic 3D Gaussian Fields for Urban Areas">A.2 Method</a></li> <li class="ltx_tocentry ltx_tocentry_subsection"><a class="ltx_ref" href="https://arxiv.org/html/2406.03175v1#A1.SS3" title="In Appendix A Appendix ‣ Dynamic 3D Gaussian Fields for Urban Areas">A.3 Experiments</a></li> </ol> </li> </ol></nav> </nav> <div class="ltx_page_main"> <div class="ltx_page_content"> <article class="ltx_document ltx_authors_1line" lang="en"> <h1 class="ltx_title ltx_title_document">Dynamic 3D Gaussian Fields for Urban Areas</h1> <div class="ltx_authors"> Tobias Fischer1 Jonas Kulhanek1,3 Samuel Rota Bulò2 Lorenzo Porzi2 Marc Pollefeys1 Peter Kontschieder2 1 ETH Zürich 2 Meta Reality Labs 3 CTU Prague <a class="ltx_ref ltx_url ltx_font_typewriter" href="https://tobiasfshr.github.io/pub/4dgf/" style="font-size:90%;" title="">https://tobiasfshr.github.io/pub/4dgf/</a> </div> <div class="ltx_abstract"> <h6 class="ltx_title ltx_title_abstract">Abstract</h6> We present an efficient neural 3D scene representation for novel-view synthesis (NVS) in large-scale, dynamic urban areas. Existing works are not well suited for applications like mixed-reality or closed-loop simulation due to their limited visual quality and non-interactive rendering speeds. Recently, rasterization-based approaches have achieved high-quality NVS at impressive speeds. However, these methods are limited to small-scale, homogeneous data, i.e. they cannot handle severe appearance and geometry variations due to weather, season, and lighting and do not scale to larger, dynamic areas with thousands of images. We propose 4DGF, a neural scene representation that scales to large-scale dynamic urban areas, handles heterogeneous input data, and substantially improves rendering speeds. We use 3D Gaussians as an efficient geometry scaffold while relying on neural fields as a compact and flexible appearance model. We integrate scene dynamics via a scene graph at global scale while modeling articulated motions on a local level via deformations. This decomposed approach enables flexible scene composition suitable for real-world applications. In experiments, we surpass the state-of-the-art by over 3 dB in PSNR and more than <math alttext="200\times" class="ltx_math_unparsed" display="inline" id="id10.1.1.m1.1"><semantics id="id10.1.1.m1.1a"><mrow id="id10.1.1.m1.1b"><mn id="id10.1.1.m1.1.1">200</mn><mo id="id10.1.1.m1.1.2" lspace="0.222em">×</mo></mrow><annotation encoding="application/x-tex" id="id10.1.1.m1.1c">200\times</annotation><annotation encoding="application/x-llamapun" id="id10.1.1.m1.1d">200 ×</annotation></semantics></math> in rendering speed. </div> <figure class="ltx_figure" id="S0.F1"><img alt="Refer to caption" class="ltx_graphics ltx_centering ltx_img_landscape" height="308" id="S0.F1.g1" src="x1.png" width="830"/> <figcaption class="ltx_caption ltx_centering">Figure 1: Summary. Given a set of heterogeneous input sequences that capture a common geographic area in varying environmental conditions (e.g. weather, season, and lighting) with distinct dynamic objects (e.g.<span cl

The 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.

Try this prompt now

Open it inside the generator with the prompt pre-filled.

Try this prompt

Related prompts

Text to Figure

Urban Dynamic Scene 3D Gaussians — Poster

Paper context

The prompt

Try this prompt now

Related prompts

PINN Framework Pipeline for Microscopy Data

DP-FTRL Privacy Amplification Analysis — Conference Poster

NC-TTT: Noise-Contrastive Test-Time Training Poster