Human Video Translation via Query Warping

arXiv:2402.12099v1 Announce Type: new
Abstract: In this paper, we present QueryWarp, a novel framework for temporally coherent human motion video translation. Existing diffusion-based video editing approaches that rely solely on key and value tokens to ensure temporal consistency, which scarifies the preservation of local and structural regions. In contrast, we aim to consider complementary query priors by constructing the temporal correlations among query tokens from different frames. Initially, we extract appearance flows from source poses to capture continuous human foreground …

abstract aim arxiv contrast cs.cv diffusion editing framework human key novel paper preservation query temporal tokens translation type value via video