| <!doctype html> |
| <html lang="en"> |
| <head> |
| <meta charset="utf-8"> |
| <meta name="viewport" content="width=device-width, initial-scale=1"> |
| <title>LiveStre4m: Feed-Forward Live Streaming of Novel Views from Unposed Multi-View Video</title> |
| <link rel="stylesheet" href="style.css?v=5"> |
| <style> |
| |
| .results-table-container { overflow-x: auto; margin-bottom: 24px; } |
| table { width: 100%; border-collapse: collapse; font-size: 0.92rem; margin-top: 12px; } |
| th, td { padding: 10px 14px; border-bottom: 1px solid #eee; text-align: left; } |
| th { font-weight: 600; color: #1f2937; background-color: #fafafa; } |
| tbody tr:hover { background-color: #f9f9f9; } |
| h3 { font-size: 1.15rem; margin: 24px 0 8px; } |
| </style> |
| </head> |
|
|
| <body> |
| <div class="container"> |
| <header class="hero"> |
| <h1>LiveStre4m: Feed-Forward Live Streaming of Novel Views from Unposed Multi-View Video</h1> |
|
|
| <p class="venue">3DMV@CVPRW 2026</p> |
|
|
| <p class="authors"> |
| <a class="author-link" href="https://www.tue.nl/en/research/researchers/pedro-quesado-dos-santos" target="_blank" rel="noopener">Pedro Quesado</a><sup>1</sup><span class="comma">,</span> |
| <a class="author-link" href="https://research.tue.nl/en/persons/erkut-akdag/" target="_blank" rel="noopener">Erkut Akdag</a><sup>1</sup><span class="comma">,</span> |
| <a class="author-link" href="#" target="_blank" rel="noopener">Yasaman Kashefbahrami</a><sup>1</sup><span class="comma">,</span> |
| <a class="author-link" href="#" target="_blank" rel="noopener">Willem Menu</a><sup>1</sup><span class="comma">,</span> |
| <a class="author-link" href="https://www.tue.nl/en/research/researchers/egor-bondarau" target="_blank" rel="noopener">Egor Bondarev</a><sup>1</sup> |
| </p> |
|
|
| <p class="affiliations"> |
| <span class="dept"><sup>1</sup>AIMSGroup, Department of Electrical Engineering, Eindhoven University of Technology</span> |
| </p> |
|
|
| <nav class="linkrow" aria-label="Project links"> |
| <a class="pill pill-dark" href="https://arxiv.org/abs/2604.06740" target="_blank" rel="noopener"> |
| <span class="pill-icon" aria-hidden="true"> |
| <svg viewBox="0 0 24 24" width="18" height="18" role="img" focusable="false" aria-label="Paper"> |
| <path d="M6 2h9l5 5v15a2 2 0 0 1-2 2H6a2 2 0 0 1-2-2V4a2 2 0 0 1 2-2zm8 1.5V8h4.5" /> |
| <path d="M8 12h8M8 16h8M8 20h6" /> |
| </svg> |
| </span> |
| <span class="pill-text">arXiv</span> |
| </a> |
|
|
| <a class="pill pill-dark" href="https://github.com/pedro-quesado/LiveStre4m" target="_blank" rel="noopener"> |
| <span class="pill-icon" aria-hidden="true"> |
| <svg viewBox="0 0 16 16" width="18" height="18" role="img" focusable="false" aria-label="GitHub"> |
| <path d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27s1.36.09 2 .27c1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0 0 16 8c0-4.42-3.58-8-8-8Z"></path> |
| </svg> |
| </span> |
| <span class="pill-text">Code</span> |
| </a> |
| </nav> |
| </header> |
|
|
| <section> |
| <h2>Overview</h2> |
| <p> |
| LiveStre4m is a feed-forward model for real-time novel view synthesis (NVS) that enables temporally consistent live streaming from as few as two unposed, sparse multi-view inputs by predicting camera parameters directly from RGB images. By combining a multi-view vision transformer for 3D scene reconstruction with a diffusion-transformer interpolation module, the system achieves an average reconstruction time of 0.07s per frame at 1024x768 resolution, vastly outperforming optimization-based dynamic scene representation methods in runtime. |
| </p> |
|
|
| <img class="figure" src="assets/intro.png" alt="Method overview"> |
| <p class="caption"> |
| Figure 1. Illustration of the proposed LiveStre4m method, a feed-forward model for live-streaming novel viewpoint video from two or more low-resolution input streams. |
| </p> |
| </section> |
|
|
| <section> |
| <h2>Results</h2> |
| <p> |
| LiveStre4m prioritizes efficiency, synthesizing the target viewpoint using only two neighboring input views, without requiring optimization or ground-truth camera parameters. It demonstrates a remarkable improvement in efficiency, operating in 0.14 seconds per frame on complex dynamic scenes, approximately 55x faster than 4DGS and 19x faster than IGS. |
| </p> |
|
|
| <div class="figure-row"> |
| <div class="figure-pair"> |
| <img class="figure-sm" src="assets/results.png" alt="Qualitative results"> |
| <p class="caption"> |
| Figure 2. Qualitative results produced by LiveStre4m on dynamic scenes. |
| </p> |
| </div> |
| </div> |
|
|
| <h3>Dynamic Scene Reconstruction</h3> |
| <p>Quantitative comparison against optimization methods on the Neural3DVideo dataset on a single A100 GPU.</p> |
| <div class="results-table-container"> |
| <table> |
| <thead> |
| <tr> |
| <th>Category</th> |
| <th>Method</th> |
| <th>Runtime (s) ↓</th> |
| <th>PSNR ↑</th> |
| <th>Camera Free</th> |
| <th>#Views</th> |
| </tr> |
| </thead> |
| <tbody> |
| <tr> |
| <td><strong>Video Optimization</strong></td> |
| <td>K-planes</td> |
| <td>48.00</td> |
| <td>32.17</td> |
| <td>❌</td> |
| <td>>19</td> |
| </tr> |
| <tr> |
| <td></td> |
| <td>4DGS</td> |
| <td>7.80</td> |
| <td>32.70</td> |
| <td>❌</td> |
| <td>≥19</td> |
| </tr> |
| <tr> |
| <td></td> |
| <td>Spacetime-GS</td> |
| <td>48.00</td> |
| <td>33.71</td> |
| <td>❌</td> |
| <td>≥19</td> |
| </tr> |
| <tr> |
| <td><strong>Frame Optimization</strong></td> |
| <td>StreamRF</td> |
| <td>15.00</td> |
| <td>32.09</td> |
| <td>❌</td> |
| <td>>19</td> |
| </tr> |
| <tr> |
| <td></td> |
| <td>3DGStream</td> |
| <td>16.93</td> |
| <td>32.75</td> |
| <td>❌</td> |
| <td>≥19</td> |
| </tr> |
| <tr> |
| <td></td> |
| <td>IGS</td> |
| <td>2.67</td> |
| <td>33.89</td> |
| <td>❌</td> |
| <td>≥19</td> |
| </tr> |
| <tr> |
| <td><strong>Feed-forward</strong></td> |
| <td><strong>LiveStre4m (Ours)</strong></td> |
| <td><strong>0.14</strong></td> |
| <td>20.64</td> |
| <td>✅</td> |
| <td><strong>2</strong></td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <p class="caption" style="text-align: left;"><em>(Note: MeetRoom results follow a similar trend, where LiveStre4m operates in 0.10s using only 2 views.)</em></p> |
|
|
| <h3>Feed-Forward Scene Reconstruction</h3> |
| <p>Comparison of feed-forward, camera-free scene reconstruction methods on a single H100 GPU.</p> |
| <div class="results-table-container"> |
| <table> |
| <thead> |
| <tr> |
| <th>Dataset</th> |
| <th>Method</th> |
| <th>Runtime (s) ↓</th> |
| <th>PSNR ↑</th> |
| <th>Resolution</th> |
| <th>Pose Free</th> |
| <th>#Views</th> |
| </tr> |
| </thead> |
| <tbody> |
| <tr> |
| <td><strong>Neural3DVideo</strong></td> |
| <td>FLARE</td> |
| <td>0.249</td> |
| <td>21.45</td> |
| <td>512x384</td> |
| <td>✅</td> |
| <td>2</td> |
| </tr> |
| <tr> |
| <td></td> |
| <td><strong>LiveStre4m (Ours)</strong></td> |
| <td><strong>0.062</strong></td> |
| <td><strong>22.44</strong></td> |
| <td>512x384</td> |
| <td>✅</td> |
| <td>2</td> |
| </tr> |
| <tr> |
| <td></td> |
| <td><strong>LiveStre4m (Ours)</strong></td> |
| <td>0.074</td> |
| <td>21.11</td> |
| <td><strong>1024x768</strong></td> |
| <td>✅</td> |
| <td>2</td> |
| </tr> |
| <tr> |
| <td><strong>MeetRoom</strong></td> |
| <td>FLARE</td> |
| <td>0.243</td> |
| <td>16.65</td> |
| <td>512x384</td> |
| <td>✅</td> |
| <td>2</td> |
| </tr> |
| <tr> |
| <td></td> |
| <td><strong>LiveStre4m (Ours)</strong></td> |
| <td><strong>0.062</strong></td> |
| <td><strong>19.32</strong></td> |
| <td>512x384</td> |
| <td>✅</td> |
| <td>2</td> |
| </tr> |
| <tr> |
| <td></td> |
| <td><strong>LiveStre4m (Ours)</strong></td> |
| <td>0.074</td> |
| <td>18.65</td> |
| <td><strong>1024x768</strong></td> |
| <td>✅</td> |
| <td>2</td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| </section> |
|
|
| <section> |
| <h2>Citation</h2> |
| <pre class="bibtex">@misc{quesado2026livestre4mfeedforwardlivestreaming, |
| title={LiveStre4m: Feed-Forward Live Streaming of Novel Views from Unposed Multi-View Video}, |
| author={Pedro Quesado and Erkut Akdag and Yasaman Kashefbahrami and Willem Menu and Egor Bondarev}, |
| year={2026}, |
| eprint={2604.06740}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CV}, |
| url={https://arxiv.org/abs/2604.06740}, |
| }</pre> |
| </section |
|
|
