Development of An Efficient 3D Reconstruction Solution from Permissive Open-Source Code

• Victor Gouveia Lyra UFPE
• Adam Pinto UFPE
• Gustavo Lima UFPE
• João Paulo Lima UFRPE
• Veronica Teichrieb UFPE
• Jonysberg Peixoto Quintino UFPE
• Fabio da Silva UFPE
• André Santos UFPE
• Helder Pinho SiDi

Resumo

3D reconstruction is one of the main topics in computer vision and is heavily applied for creating virtual environments. Photogrammetry is a technique for obtaining 3D information by mapping objects and scenarios using only images. However, this process can take long time to process when using large datasets with non-commercial solutions. In this paper, a permissive open-source pipeline is proposed focusing on robustness, efficiency, and low execution time in batch processing. The permissive license allows the commercial use without the need of keep the code open. We mixed an enhanced structure from motion algorithm and a recurrent multi-view reconstruction. We also use Point Cloud Library for normal estimation, surface reconstruction, and texture mapping. We compared the results of COLMAP and MVE techniques using the DTU MVS dataset and real-world scenarios with our own datasets. The results showed a decrease of 69.4% on average time (compared to the best result of other techniques), but also demonstrated the need for more images to generate a complete reconstructed model.

Palavras-chave: reconstruction, photogrammetry, permissive license, batch, texture