Rainyscape: Unsupervised rainy scene reconstruction using decoupled neural rendering
Author(s)
Author(s)
Lyu, X.
Hou, J.
Date Issued
2024
Publisher
Association for Computing Machinery
Related Publication(s)
Proceedings of the 32nd ACM International Conference on Multimedia (MM '24)
Start page
10920
End page
10929
Abstract
We propose RainyScape, an unsupervised framework to reconstruct pristine 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, leveraging 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, source code, and supplementary material are publicly available at https://github.com/lyuxianqiang/RainyScape.
SFU Affiliated Publication
Yes
Availability at SFU Library
No database links found.