L²DGS：低光照动态高斯泼溅
$L^{2}DGS$: Low-Light Dynamic Gaussian Splatting
把动态高斯泼溅扩展到低光照视频，用本征分解（时变光照 × 时不变反射率）加遮挡-去遮挡网络做自监督，可直接迁移到夜间动态场景的新视角合成与4D重建。
原文依据 a self-supervised 4D GS framework that directly reconstructs well-lit dynamic scenes from low-light videos
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论由于物体与相机运动以及稀疏观测，合成动态场景的新时空视角具有挑战性。尽管近期的神经辐射场（NeRF）与高斯泼溅（GS）方法能够实现4D动态场景重建，但它们大多假设输入处于良好光照条件下。现有的低光照重建方法局限于静态场景，且主要关注亮度增强，而忽略了潜在的场景结构。从低光照输入重建光照良好的动态场景尤为困难，因为运动引起的阴影、遮挡与去遮挡使该问题高度歧义。我们提出L²DGS（低光照动态高斯泼溅），一个自监督4D GS框架，可直接从低光照视频重建光照良好的动态场景。该方法将场景分解为依赖视角与时间的光照分量以及不随视角与时间变化的反射率分量。我们引入遮挡-去遮挡网络（OCD-Net）来建模时序强度变化，并引入亮度衰减特征（BAF）及BAF增强网络（BAFE-Net），以实现光照良好观测与低光照观测之间几何与光度感知的变换，从而支持自监督。L²DGS在标准sRGB输入上运行，无需相机元数据。在模拟数据集与我们提出的真实低光照动态视频（L²DyV）数据集上的实验表明，其定性定量性能均优于先前方法。数据集见：https://github.com/akumar005/L2DGS 。
英文原文摘要 1589 字符
Synthesizing novel spatiotemporal views of dynamic scenes is challenging due to object and camera motion, and sparse observations. While recent Neural Radiance Field (NeRF) and Gaussian Splatting (GS) methods enable 4D dynamic scene reconstruction, they predominantly assume well-lit inputs. Existing low-light reconstruction approaches are limited to static scenes and mainly focus on brightness enhancement while overlooking underlying scene structure. Reconstructing well-lit dynamic scenes from low-light inputs is particularly challenging due to motion-induced shadows, occlusions, and disocclusions, making the problem highly ambiguous. We propose L^ 2 DGS (Low-Light Dynamic Gaussian Splatting), a self-supervised 4D GS framework that directly reconstructs well-lit dynamic scenes from low-light videos. The method decomposes the scene into view- and time-dependent illumination and view-time-invariant reflectance components. We introduce an Occlusion-Disocclusion Network (OCD-Net) to model temporal intensity variations and Brightness Attenuation Features (BAFs) with a BAF Enhancement Network (BAFE-Net) to enable geometry- and photometry-aware transformation between well-lit and low-light observations for self-supervision. L^ 2 DGS operates on standard sRGB inputs without requiring camera metadata. Experiments on simulated and proposed real Low-Light Dynamic Video (L^ 2 DyV) datasets demonstrate superior qualitative and quantitative performance over prior methods. The dataset is available at: \href https://github.com/akumar005/L2DGS https://github.com/akumar005/L2DGS .