0546470 20240111141056.220211012235959.9 10.1109/ICCV48922.2021.00352 9 s. E cav_un_epca*0546469978-1-6654-2812-5Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)3541-3549PiscatawayIEEE2021 tracking convolutional neural network deconvolution cav_un_auth*0352947 Rozumnyi D. CZ cav_un_auth*0075799 Matas J. CZ cav_un_auth*0101209 Šroubek Filip UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0415064 Pollefeys M. CH cav_un_auth*0415065 Oswald M.R. CH pdf http://library.utia.cas.cz/separaty/2021/ZOI/sroubek-0546470.pdf 5.5MB GA21-03921S GA ČR cav_un_auth*0412209 We propose the first learning-based approach for fast moving objects detection. Such objects are highly blurred and move over large distances within one video frame. Fast moving objects are associated with a deblurring and matting problem, also called deblatting. We show that the separation of deblatting into consecutive matting and deblurring allows achieving real-time performance, i.e. an order of magnitude speed-up, and thus enabling new classes of application. The proposed method detects fast moving objects as a truncated distance function to the trajectory by learning from synthetic data. For the sharp appearance estimation and accurate trajectory estimation, we propose a matting and fitting network that estimates the blurred appearance without background, followed by an energy minimization based deblurring. The state-of-the-art methods are outperformed in terms of recall, precision, trajectory estimation, and sharp appearance reconstruction. Compared to other methods, such as deblatting, the inference is of several orders of magnitude faster and allows applications such as real-time fast moving object detection and retrieval in large video collections. cav_un_auth*0415066 International Conference on Computer Vision (ICCV) 2021 20211011 20211017 Piscataway (on-line) US JD 20000 20200 20206 2022 5 PO RVO:67985556 http://hdl.handle.net/11104/0323758 cav_un_auth*0376357 ČVUT Fakulta elektrotechnická ČVUT FEL CZ cav_un_auth*0376740 ETH Zürich S 2021 SCOPUS PUBMED WOS pdf 5.5MB cav_un_epca*0546469 Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) IEEE 2021 Piscataway 3541 3549 978-1-6654-2812-5 2380-7504