Automation in photogrammetric 3D reconstruction

Automated image-based 3D reconstruction methods are everyday flooding our 3D modelling applications. Fully automated solutions give more and more the impression that from a sample of randomly acquired images we can derive nice-looking 3D models. Although the level of automation is reaching very high standards, image quality is a fundamental pre-requisite to produce successful and photo-realistic 3D products, in particular when dealing with large datasets of images. This research investigates: (i) the pre-processing phase related to colour enhancement, image denoising, colour-to-grey conversion and image content enrichment, (ii) the tie point extraction phase with the various operators and (iii) the dense matching step with all the different methods. The various evaluations and assessments prove the potentialities and open issues of close-range photogrammetry for 3D reconstruction purposes.

Representative Publications:

- F. Bellavia, L. Morelli, F. Menna, and F. Remondino, 2022: Image orientation with a hybrid pipeline robust to rotations and wide-baselines. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVI-2/W1-2022, 73–80

- Remondino, F., Menna, F., and Morelli, L., 2021: Evaluating hand-crafted and learning-based features for photogrammetric applications. ISPRS Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2021, 549–556

- Mousavi, V., Varshosaz. M., Remondino, F., 2021: Using Information Content to Select Keypoints for UAV Image Matching. Remote Sensing, Vol.13(7):1302

- Nocerino, E., Stathopoulou, E.K., Rigon, S., Remondino, F., 2020: Surface Reconstruction Assessment in Photogrammetric Applications. MDPI Sensors, 20(20), 5863

- Knyaz, V.A., Kniaz, V.V., Remondino, F., Zheltov, S.Y., Gruen, A., 2020: 3D Reconstruction of a Complex Grid Structure Combining UAS Images and Deep Learning. MDPI Remote Sensing, 12(19), 3128

- Stathopoulou, E.K. and Remondino, F., 2019. Open-source image-based 3D reconstruction pipelines: Review, comparison and evaluation. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W17, 331–338

- Remondino, F., Nocerino, E., Toschi, I., Menna, F., 2017: A critical review of automated photogrammetric processing of large datasets. ISPRS Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., Vol. XLII-2/W5, pp. 591-599. 26th CIPA Symposium, Ottawa, Canada

- Remondino, F., Gaiani, M., Apollonio, F., Ballabeni, A., Ballabeni, M., Morabito, D., 2016: 3D Documentation of 40 Kilometers of Historical Porticoes - the Challenge. ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XLI-B5, pp. 711-718

- Gaiani, M., Remondino, F., Apollonio, F., Ballabeni, A., 2016: An advanced pre-processing pipeline to improve automated photogrammetric reconstructions of architectural scenes. Remote Sensing, Vol. 8(3), 178; doi: 10.3390/rs8030178

- Ballabeni, A., Apollonio, F. I., Gaiani, M., Remondino, F., 2015: Advances in image pre-processing to improve automated 3D reconstruction. ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XL-5/W4, pp. 315-323. ISPRS 3D-ARCH 2015 workshop, 25–27 February 2015, Avila, Spain

- Remondino, F., Spera, M.G., Nocerino, E., Menna, F., Nex, F., 2014: State of the art in high density image matching. The Photogrammetric Record, Vol. 29(146), pp. 144-166, DOI: 10.1111/phor.12063

- Apollonio, F., Ballabeni, A., Gaiani, M., Remondino, F., 2014: Evaluation of feature-based methods for automated network orientation. ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XL-5, pp. 47-54. ISPRS Commission V Symposium, 23–25 June 2014, Riva del Garda, Italy

Funding: internal