In this work, we propose the use of the Neural Gas (NG), a neural network that uses an unsupervised competitive hebbian learning (CHL), to develop a reverse engineering process. This is a simple and accurate method to reconstruct objects from the point cloud obtained from overlapped multiple views using low cost sensors. In contrast to other methods that may need several stages that include downsampling, noise filtering and many other tasks, the NG automatically obtains the 3D model of the scanned objects.To demonstrate the validity of our proposal we tested our method with several models and performed a study of the neural network parameterization calculating the quality of representation and also comparing results with other neural methods like Growing Neural Gas and Kohonen maps or clasical Email addresses: sorts@dtic.ua.es (Sergio Orts-Escolano), jgarcia@dtic.ua.es (Jose Garcia-Rodriguez), jimeno@dtic.ua.es (Antonio Jimeno-Morenilla), jserra@dtic.ua.es (Jose Antonio Serra-Perez), agg180@alu.ua.es (Alberto Garcia), vmorell@dccia.ua.es (Vicente Morell), miguel@dccia.ua.es (Miguel Cazorla) Preprint submitted to Applied Soft Computing January 7, 2015 methods like Voxel Grid. We also reconstructed models acquired by low cost sensors that can be included in virtual and augmented reality environments to redesign or manipulation purpose. Since the NG algorithm has a strong computational cost we propose its acceleration. We have redesigned and implemented the NG learning algorithm to fit it onto a Graphic Processor Unit using CUDA. A speed-up of 180x faster is obtained compared to the sequential CPU version.