Neural Radiance Fields (NeRFs) have revolutionized 3D scene reconstruction by enabling photorealistic rendering from novel viewpoints. Despite their success, applying NeRFs to detailed 3D car model reconstruction has been limited due to practical challenges. Traditional methods like LiDAR scanning and photogrammetry, while accurate, are cost-prohibitive and require specialized equipment, hindering widespread adoption. Manual 3D modeling is another route but is labor-intensive and often inconsistent.Our project introduces an innovative application of NeRFs for reconstructing detailed 3D car models using only standard camera equipment. By capturing multiple images from various angles and employing advanced techniques such as structure-from-motion for precise camera pose estimation, we achieve high-fidelity reconstructions of car geometries.Building upon our initial findings, several key improvements were implemented. The NeRF architecture was optimized to enhance clarity, enabling finer detail capture in complex regions like reflective surfaces and intricate design elements. Additionally, we integrated accelerated training algorithms and efficient data preprocessing steps to significantly reduce computation time, addressing previous speed limitations.The resulting models facilitate interactive rendering from any viewpoint and can be seamlessly integrated into applications for automotive design, virtual showrooms, and augmented reality (AR). The method adopted in this work not only provides a cost-effective and scalable solution but also maintains high accuracy and detail. Experimental results confirm that our improved NeRF-based approach outperforms earlier models in both quality and efficiency. This advancement demonstrates NeRF's potential as a transformative tool in the automotive industry for creating accessible and detailed 3D car models. We will present a comprehensive analysis of our methodology, detailed results, and the developed software at the conference, highlighting the practical implications and future applications of our work.