Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction
This work addresses video prediction for arbitrary objects without costly keypoint labeling, but it is incremental as it builds on existing unsupervised and conditional prediction approaches.
The paper tackles the problem of generating future video frames from a single image and action class by using unsupervised keypoint detection to guide motion prediction, achieving more realistic results compared to previous methods.
We propose a deep video prediction model conditioned on a single image and an action class. To generate future frames, we first detect keypoints of a moving object and predict future motion as a sequence of keypoints. The input image is then translated following the predicted keypoints sequence to compose future frames. Detecting the keypoints is central to our algorithm, and our method is trained to detect the keypoints of arbitrary objects in an unsupervised manner. Moreover, the detected keypoints of the original videos are used as pseudo-labels to learn the motion of objects. Experimental results show that our method is successfully applied to various datasets without the cost of labeling keypoints in videos. The detected keypoints are similar to human-annotated labels, and prediction results are more realistic compared to the previous methods.