Rethinking Rainy 3D Scene Reconstruction via Perspective Transforming and Brightness Tuning
This addresses the challenge of rainy 3D scene reconstruction for computer vision applications, but it is incremental as it builds on existing 3D Gaussian splatting methods with new dataset and integration.
The paper tackles the problem of inaccurate 3D scene reconstruction from rain-degraded multi-view images by constructing the OmniRain3D dataset with perspective and brightness variations and proposing the REVR-GSNet framework, which achieves high-fidelity reconstruction of clean 3D scenes.
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.