International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | A Survey on Multi-Weather Image Generation using Generative Deep Models |
|---|---|
| ABSTRACT | Weather conditions such as rain, fog, snow, night, dawn, and dusk strongly affect the quality of outdoor images. These conditions reduce visibility and limit the performance of computer vision systems. In recent years, many deep learning and GAN-based models have been developed to generate or simulate different weather effects. These models help researchers evaluate vision algorithms and train systems to work reliably in multiple environments. This review paper provides an overview of weather-influenced image-generation techniques across different weather types. We compare popular methods, discuss the datasets used, and highlight the strengths and limitations of each approach. The paper also summarizes experimental results reported in the literature and outlines future research directions for more realistic and efficient weather-conditioned image synthesis. |
| AUTHOR | LAKSHMITHA H Y Assistant Professor, DoS in Computer Science, SBRR Mahajana First Grade College (Autonomous) PG Wing, Pooja Bhagavat Memorial Mahajana Education Centre, Mysore, Karnataka, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312030 |
| pdf/30_A Survey on Multi-Weather Image Generation using Generative Deep Models.pdf | |
| KEYWORDS |
