The paper presents a novel approach to single image de-raining using Conditional Generative Adversarial Networks (CGANs). The authors address the ill-posed nature of the de-raining problem by leveraging the generative capabilities of CGANs, which enforce an additional constraint that the de-rained image must be indistinguishable from the ground truth clean image. The proposed method, called Image De-raining Conditional Generative Adversarial Network (ID-CGAN), includes a new refined loss function and architectural innovations in the generator-discriminator pair to improve visual quality and quantitative performance. The generator is constructed using densely connected networks, while the discriminator is designed to capture both global and local information. Experiments on synthetic and real images show that the proposed method outperforms existing state-of-the-art methods in terms of both visual quality and quantitative metrics. Additionally, the effectiveness of the method in improving object detection performance on rainy images is demonstrated using the Faster-RCNN algorithm.The paper presents a novel approach to single image de-raining using Conditional Generative Adversarial Networks (CGANs). The authors address the ill-posed nature of the de-raining problem by leveraging the generative capabilities of CGANs, which enforce an additional constraint that the de-rained image must be indistinguishable from the ground truth clean image. The proposed method, called Image De-raining Conditional Generative Adversarial Network (ID-CGAN), includes a new refined loss function and architectural innovations in the generator-discriminator pair to improve visual quality and quantitative performance. The generator is constructed using densely connected networks, while the discriminator is designed to capture both global and local information. Experiments on synthetic and real images show that the proposed method outperforms existing state-of-the-art methods in terms of both visual quality and quantitative metrics. Additionally, the effectiveness of the method in improving object detection performance on rainy images is demonstrated using the Faster-RCNN algorithm.