TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models

TL;DR

TCAN is a novel pose-driven human image animation method that achieves temporal consistency and robustness to pose detection errors by leveraging pre-trained diffusion models, LoRA adaptation, and a temporal layer.

Contribution

It introduces a method that uses frozen ControlNet with LoRA and a temporal layer to improve human image animation robustness and consistency without fine-tuning the pre-trained model.

Findings

Achieves high-quality, temporally consistent human video synthesis.

Robust to erroneous pose detections and outliers.

Effective across various pose scenarios like chibi.

Abstract

Pose-driven human-image animation diffusion models have shown remarkable capabilities in realistic human video synthesis. Despite the promising results achieved by previous approaches, challenges persist in achieving temporally consistent animation and ensuring robustness with off-the-shelf pose detectors. In this paper, we present TCAN, a pose-driven human image animation method that is robust to erroneous poses and consistent over time. In contrast to previous methods, we utilize the pre-trained ControlNet without fine-tuning to leverage its extensive pre-acquired knowledge from numerous pose-image-caption pairs. To keep the ControlNet frozen, we adapt LoRA to the UNet layers, enabling the network to align the latent space between the pose and appearance features. Additionally, by introducing an additional temporal layer to the ControlNet, we enhance robustness against outliers of the pose detector. Through the analysis of attention maps over the temporal axis, we also designed a novel temperature map leveraging pose information, allowing for a more static background. Extensive experiments demonstrate that the proposed method can achieve promising results in video synthesis tasks encompassing various poses, like chibi. Project Page: https://eccv2024tcan.github.io/