Rethinking Rainy 3D Scene Reconstruction via Perspective Transforming and Brightness Tuning
Authors:
Preprint
Abstract
Rain degrades the visual quality of multi-view images, which are essential for 3D scene reconstruction, resulting in inaccurate and incomplete reconstruction results. Existing datasets often overlook two critical characteristics of real rainy 3D scenes: the viewpoint-dependent variation in the appearance of rain streaks caused by their projection onto 2D images, and the reduction in ambient brightness resulting from cloud coverage during rainfall. To improve data realism, we construct a new dataset named OmniRain3D that incorporates perspective heterogeneity and brightness dynamicity, enabling more faithful simulation of rain degradation in 3D scenes. Based on this dataset, we propose an end-to-end reconstruction framework named REVR-GSNet (Rain Elimination and Visibility Recovery for 3D Gaussian Splatting). Specifically, REVR-GSNet integrates recursive brightness enhancement, Gaussian primitive optimization, and GS-guided rain elimination into a unified architecture through joint alternating optimization, achieving high-fidelity reconstruction of clean 3D scenes from rain-degraded inputs. Extensive experiments show the effectiveness of our dataset and method. Our dataset and method provide a foundation for future research on multi-view image deraining and rainy 3D scene reconstruction.Keywords
All Related Versions
This publication has 47 references indexed in Scilit:
- Exploring the impact of rainfall intensity on the attenuation-rainfall relationshipJournal of Quantitative Spectroscopy and Radiative Transfer, 2025
- Exploring a context-gated network for effective image derainingJournal of Visual Communication and Image Representation, 2024
- Exploring an efficient frequency-guidance transformer for single image derainingSignal, Image and Video Processing, 2023
- Selective generative adversarial network for raindrop removal from a single imageNeurocomputing, 2021
- Rain Rendering for Evaluating and Improving Robustness to Bad WeatherInternational Journal of Computer Vision, 2020
- Rain or Snow Detection in Image Sequences Through Use of a Histogram of Orientation of StreaksInternational Journal of Computer Vision, 2011
- Analysis of Rain and Snow in Frequency SpaceInternational Journal of Computer Vision, 2009
- Real-time modeling and rendering of raining scenesThe Visual Computer, 2008
- Using the Shape Characteristics of Rain to Identify and Remove Rain from Video2008
- Vision and RainInternational Journal of Computer Vision, 2007