TY - GEN
T1 - Click to Move
T2 - 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021
AU - Ardino, Pierfrancesco
AU - De Nadai, Marco
AU - Lepri, Bruno
AU - Ricci, Elisa
AU - Lathuilière, Stéphane
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021/1/1
Y1 - 2021/1/1
N2 - This paper introduces Click to Move (C2M), a novel framework for video generation where the user can control the motion of the synthesized video through mouse clicks specifying simple object trajectories of the key objects in the scene. Our model receives as input an initial frame, its corresponding segmentation map and the sparse motion vectors encoding the input provided by the user. It outputs a plausible video sequence starting from the given frame and with a motion that is consistent with user input. Notably, our proposed deep architecture incorporates a Graph Convolution Network (GCN) modelling the movements of all the objects in the scene in a holistic manner and effectively combining the sparse user motion information and image features. Experimental results show that C2M outperforms existing methods on two publicly available datasets, thus demonstrating the effectiveness of our GCN framework at modelling object interactions. The source code is publicly available at https://github.com/PierfrancescoArdino/C2M.
AB - This paper introduces Click to Move (C2M), a novel framework for video generation where the user can control the motion of the synthesized video through mouse clicks specifying simple object trajectories of the key objects in the scene. Our model receives as input an initial frame, its corresponding segmentation map and the sparse motion vectors encoding the input provided by the user. It outputs a plausible video sequence starting from the given frame and with a motion that is consistent with user input. Notably, our proposed deep architecture incorporates a Graph Convolution Network (GCN) modelling the movements of all the objects in the scene in a holistic manner and effectively combining the sparse user motion information and image features. Experimental results show that C2M outperforms existing methods on two publicly available datasets, thus demonstrating the effectiveness of our GCN framework at modelling object interactions. The source code is publicly available at https://github.com/PierfrancescoArdino/C2M.
U2 - 10.1109/ICCV48922.2021.01448
DO - 10.1109/ICCV48922.2021.01448
M3 - Conference contribution
AN - SCOPUS:85127815298
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 14729
EP - 14738
BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 11 October 2021 through 17 October 2021
ER -