https://vilab.team/tag/retinex%E5%85%88%E9%AA%8C/ Retinex先验 Hugo Blox Builder (https://hugoblox.com)en-usSat, 14 Mar 2026 00:00:00 +0000 https://vilab.team/media/icon_hu2896232876136423579.png https://vilab.team/tag/retinex%E5%85%88%E9%AA%8C/ https://vilab.team/publication/seeing-the-unseen-zooming-in-the-dark-with-event-cameras/ Sat, 14 Mar 2026 00:00:00 +0000 https://vilab.team/publication/seeing-the-unseen-zooming-in-the-dark-with-event-cameras/ <p>本文提出RetinexEVSR，首个事件驱动的低光视频超分辨率框架。该框架利用高对比度事件信号与Retinex先验，通过双向跨模态融合策略，有效整合噪声事件数据与退化RGB帧中的有用信息。其中，照明引导事件增强模块利用Retinex模型导出的光照图逐步细化事件特征，抑制低光伪影并保留高对比度细节；事件引导反射率增强模块则通过多尺度融合机制动态恢复反射率细节。实验表明，该方法在三个数据集上达到最优性能，在SDSD基准上相比先前事件方法提升2.95 dB，并减少65%运行时间。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-aaai/ Sat, 14 Mar 2026 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-aaai/ <p>热烈祝贺开大纯同学！论文《Seeing the unseen: Zooming in the dark with event cameras》已发表在 <em>AAAI 2026</em>。</p> <h2 id="seeing-the-unseen-zooming-in-the-dark-with-event-cameras">Seeing the unseen: Zooming in the dark with event cameras</h2> <p><strong>祝贺开大纯同学！该论文已发表在 <em>AAAI</em>。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Seeing the unseen: Zooming in the dark with event cameras" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-aaai/images/paper-01_hu13636376305985334282.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-aaai/images/paper-01_hu16933069341322044714.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-aaai/images/paper-01_hu642809347018091764.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-aaai/images/paper-01_hu13636376305985334282.webp" width="760" height="391" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Dachun Kai、Zeyu Xiao、Huyue Zhu、Jiaxiao Wang、Yueyi Zhang、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>AAAI</em></li> <li><strong>发表时间：</strong> 2026年3月14日</li> <li><strong>相关链接：</strong> <a href="https://ojs.aaai.org/index.php/AAAI/article/view/37478" target="_blank" rel="noopener">论文链接</a> · <a href="https://ojs.aaai.org/index.php/AAAI/article/download/37478/41440" target="_blank" rel="noopener">PDF</a> · <a href="https://github.com/DachunKai/RetinexEVSR" target="_blank" rel="noopener">代码</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文提出RetinexEVSR，首个事件驱动的低光视频超分辨率框架。该框架利用高对比度事件信号与Retinex先验，通过双向跨模态融合策略，有效整合噪声事件数据与退化RGB帧中的有用信息。其中，照明引导事件增强模块利用Retinex模型导出的光照图逐步细化事件特征，抑制低光伪影并保留高对比度细节；事件引导反射率增强模块则通过多尺度融合机制动态恢复反射率细节。实验表明，该方法在三个数据集上达到最优性能，在SDSD基准上相比先前事件方法提升2.95 dB，并减少65%运行时间。</p>