Intrinsic Temporal Regularization for High-resolution Human Video Synthesis

Abstract: Temporal consistency is crucial for extending image processing pipelines to the video domain, which is often enforced with flow-based warping error over adjacent frames. Yet for human video synthesis, such scheme is less reliable due to the misalignment between source and target video as well as the difficulty in accurate flow estimation. In this paper, we propose an effective intrinsic temporal regularization scheme to mitigate these issues, where an intrinsic confidence map is estimated via the frame generator to regulate motion estimation via temporal loss modulation. This creates a shortcut for back-propagating temporal loss gradients directly to the front-end motion estimator, thus improving training stability and temporal coherence in output videos. We apply our intrinsic temporal regulation to single-image generator, leading to a powerful "INTERnet" capable of generating $512\times512$ resolution human action videos with temporal-coherent, realistic visual details. Extensive experiments demonstrate the superiority of proposed INTERnet over several competitive baselines.