Bidirectional Temporal Diffusion Model for Temporally Consistent Human Animation

Authors
Tserendorj AdiyaJae Shin YoonLee JeongEunKim Sang HunHwasup Lim
Issue Date
2024-05-09
Publisher
International Conference on Learning Representations (ICLR)
Citation
International Conference on Learning Representations (ICLR)
Abstract
We introduce a method to generate temporally coherent human animation from a single image, a video, or a random noise.This problem has been formulated as modeling of an auto-regressive generation, i.e., to regress past frames to decode future frames.However, such unidirectional generation is highly prone to motion drifting over time, generating unrealistic human animation with significant artifacts such as appearance distortion. We claim that bidirectional temporal modeling enforces temporal coherence on a generative network by largely suppressing the appearance ambiguity.To prove our claim, we design a novel human animation framework using a denoising diffusion model: a neural network learns to generate the image of a person by denoising temporal Gaussian noises whose intermediate results are cross-conditioned bidirectionally between consecutive frames. In the experiments, our method demonstrates strong performance compared to existing unidirectional approaches with realistic temporal coherence.
URI

Go to Link
Appears in Collections:
KIST Conference Paper > 2024
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE