You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
FaceFusion is an AI-powered tool that delivers high-quality face enhancements and realistic face swaps. Using models like GFPGAN, Real-ESRGAN, and InsightFace, it’s perfect for film studios, content creators, and designers seeking efficient and affordable visual effects if developed fully.
Developed VisionSoC, an advanced image upscaling model using Enhanced Super Resolution Generative Adversarial Networks (ESRGAN) with Python, leveraging frameworks such as TensorFlow and Keras. Created a comprehensive web-based application for the model using HTML, CSS, and JavaScript, and integrated the frontend with the backend using Flask.
Object Detection project leverages the YOLOv3 model with OpenCV to detect and label objects in images, applying non-maximum suppression for accurate results. It involves loading the model, preprocessing input images, and visualizing detected objects with bounding boxes and labels.