5 papers
Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis
Chenghao Qian, Nedko Savov, Lingdong Kong +7
Weather synthesis aims to add weather effects to input videos while preserving scene identity, structure, and motion. The key limitation of existing methods is the lack of diversit…
WeatherEdit: Controllable Weather Editing with 4D Gaussian Field
Chenghao Qian, Wenjing Li, Yuhu Guo +1
In this work, we present WeatherEdit, a novel weather editing pipeline for generating realistic weather effects with controllable types and severity in 3D scenes. Our approach is s…
WeatherGS: 3D Scene Reconstruction in Adverse Weather Conditions via Gaussian Splatting
Chenghao Qian, Yuhu Guo, Wenjing Li +1
3D Gaussian Splatting (3DGS) has gained significant attention for 3D scene reconstruction, but still suffers from complex outdoor environments, especially under adverse weather. Th…
WeatherDG: LLM-assisted Diffusion Model for Procedural Weather Generation in Domain-Generalized Semantic Segmentation
Chenghao Qian, Yuhu Guo, Yuhong Mo +1
In this work, we propose a novel approach, namely WeatherDG, that can generate realistic, weather-diverse, and driving-screen images based on the cooperation of two foundation mode…
AllWeatherNet:Unified Image Enhancement for Autonomous Driving under Adverse Weather and Lowlight-conditions
Chenghao Qian, Mahdi Rezaei, Saeed Anwar +4
Adverse conditions like snow, rain, nighttime, and fog, pose challenges for autonomous driving perception systems. Existing methods have limited effectiveness in improving essentia…