WeatherDiffusion: Weather-Guided Diffusion Model for Forward and Inverse Rendering
This work addresses the problem of robust scene understanding and reconstruction for autonomous driving in adverse weather conditions, offering incremental improvements through a novel attention mechanism and new datasets.
The paper tackles the challenge of forward and inverse rendering in autonomous driving scenes under complex weather and lighting by introducing WeatherDiffusion, a diffusion-based framework that enables authentic estimation of material properties, scene geometry, and lighting, and supports controllable editing, outperforming state-of-the-art methods on benchmarks.
Forward and inverse rendering have emerged as key techniques for enabling understanding and reconstruction in the context of autonomous driving (AD). However, complex weather and illumination pose great challenges to this task. The emergence of large diffusion models has shown promise in achieving reasonable results through learning from 2D priors, but these models are difficult to control and lack robustness. In this paper, we introduce WeatherDiffusion, a diffusion-based framework for forward and inverse rendering on AD scenes with various weather and lighting conditions. Our method enables authentic estimation of material properties, scene geometry, and lighting, and further supports controllable weather and illumination editing through the use of predicted intrinsic maps guided by text descriptions. We observe that different intrinsic maps should correspond to different regions of the original image. Based on this observation, we propose Intrinsic map-aware attention (MAA) to enable high-quality inverse rendering. Additionally, we introduce a synthetic dataset (\ie WeatherSynthetic) and a real-world dataset (\ie WeatherReal) for forward and inverse rendering on AD scenes with diverse weather and lighting. Extensive experiments show that our WeatherDiffusion outperforms state-of-the-art methods on several benchmarks. Moreover, our method demonstrates significant value in downstream tasks for AD, enhancing the robustness of object detection and image segmentation in challenging weather scenarios.