o:2436 Comparative evaluation of keypoint detectors for 3d digital avatar reconstruction en Three-dimensional personalized human avatars have been successfully utilized in shopping, entertainment, education, and health applications. However, it is still a challenging task to obtain both a complete and highly detailed avatar automatically. One approach is to use general-purpose, photogrammetry-based algorithms on a series of overlapping images of the person. We argue that the quality of avatar reconstruction can be increased by modifying parts of the photogrammetry-based algorithm pipeline to be more specifically tailored to the human body shape. In this context, we perform an extensive, standalone evaluation of eleven algorithms for keypoint detection, which is the first phase of the photogrammetry-based reconstruction pipeline. We include well established, patented Distinctive image features from scale-invariant keypoints (SIFT) and Speeded up robust features (SURF) detection algorithms as a baseline since they are widely incorporated into photogrammetry-based software. All experiments are conducted on a dataset of 378 images of human body captured in a controlled, multi-view stereo setup. Our findings are that binary detectors highly outperform commonly used SIFT-like detectors in the avatar reconstruction task, both in terms of detection speed and in number of detected keypoints. 1552099 10.2298/FUEE2003379G 1552101 2683-3867 2023-06-28T22:26:06.824Z 44 no 46 Dušan Gajić University of Novi Sad, Faculty of Technical Sciences 0000-0003-0495-8788 Gorana Gojić University of Novi Sad, Faculty of Technical Sciences person 0000-0002-6100-5871 Dinu Dragan University of Novi Sad, Faculty of Technical Sciences person 0000-0001-8623-1923 Veljko Petrović University of Novi Sad, Faculty of Technical Sciences person 0000-0001-8662-1366 2020 application/pdf 810600 https://unilib.phaidrabg.rs/o:2436 no yes 1 70 92000001 2020 71A08 Comparative evaluation of keypoint detectors for 3d digital avatar reconstruction Facta universitatis - series: Electronics and EnergeticsElectronics and Energetics 33 3 379 394 2020