RainyScape：基于解耦神经渲染的无监督雨景重建
RainyScape: Unsupervised Rainy Scene Reconstruction using Decoupled Neural Rendering
AI总结：
本研究提出无监督框架RainyScape，通过解耦神经渲染与降雨预测模块，结合自适应方向敏感梯度损失，从多视角雨图中重建干净场景，在两类基准上实现最优性能。
摘要：
我们提出RainyScape，这是一种从多视角雨天图像集合中重建干净场景的无监督框架。RainyScape包含两个主要模块：神经渲染模块，以及结合了预测器网络与可学习潜嵌入的降雨预测模块，其中可学习潜嵌入用于捕捉场景的降雨特征。具体而言，基于神经网络的频谱偏置特性，我们首先优化神经渲染管线以获得低频场景表示。随后，我们在提出的自适应方向敏感梯度重建损失的驱动下，联合优化这两个模块，该损失促使网络区分场景细节与雨纹，推动梯度向相关组件传播。在经典的神经辐射场（NeRF）和近期提出的3D高斯泼溅（3D Gaussian Splatting）上开展的大量实验表明，我们的方法在有效去除雨纹、渲染干净图像方面表现优异，实现了当前最优性能。构建的高质量数据集和源代码将公开发布。
英文摘要：
We propose RainyScape, an unsupervised framework for reconstructing clean scenes from a collection of multi-view rainy images. RainyScape consists of two main modules: a neural rendering module and a rain-prediction module that incorporates a predictor network and a learnable latent embedding that captures the rain characteristics of the scene. Specifically, based on the spectral bias property of neural networks, we first optimize the neural rendering pipeline to obtain a low-frequency scene representation. Subsequently, we jointly optimize the two modules, driven by the proposed adaptive direction-sensitive gradient-based reconstruction loss, which encourages the network to distinguish between scene details and rain streaks, facilitating the propagation of gradients to the relevant components. Extensive experiments on both the classic neural radiance field and the recently proposed 3D Gaussian splatting demonstrate the superiority of our method in effectively eliminating rain streaks and rendering clean images, achieving state-of-the-art performance. The constructed high-quality dataset and source code will be publicly available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
