SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Namekata, Koichi, Bahmani, Sherwin, Wu, Ziyi, Kant, Yash, Gilitschenski, Igor, Lindell, David B.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913706469752832
author Namekata, Koichi
Bahmani, Sherwin
Wu, Ziyi
Kant, Yash
Gilitschenski, Igor
Lindell, David B.
author_facet Namekata, Koichi
Bahmani, Sherwin
Wu, Ziyi
Kant, Yash
Gilitschenski, Igor
Lindell, David B.
contents Methods for image-to-video generation have achieved impressive, photo-realistic quality. However, adjusting specific elements in generated videos, such as object motion or camera movement, is often a tedious process of trial and error, e.g., involving re-generating videos with different random seeds. Recent techniques address this issue by fine-tuning a pre-trained model to follow conditioning signals, such as bounding boxes or point trajectories. Yet, this fine-tuning procedure can be computationally expensive, and it requires datasets with annotated object motion, which can be difficult to procure. In this work, we introduce SG-I2V, a framework for controllable image-to-video generation that is self-guided$\unicode{x2013}$offering zero-shot control by relying solely on the knowledge present in a pre-trained image-to-video diffusion model without the need for fine-tuning or external knowledge. Our zero-shot method outperforms unsupervised baselines while significantly narrowing down the performance gap with supervised models in terms of visual quality and motion fidelity. Additional details and video results are available on our project page: https://kmcode1.github.io/Projects/SG-I2V
format Preprint
id arxiv_https___arxiv_org_abs_2411_04989
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation
Namekata, Koichi
Bahmani, Sherwin
Wu, Ziyi
Kant, Yash
Gilitschenski, Igor
Lindell, David B.
Computer Vision and Pattern Recognition
Machine Learning
Methods for image-to-video generation have achieved impressive, photo-realistic quality. However, adjusting specific elements in generated videos, such as object motion or camera movement, is often a tedious process of trial and error, e.g., involving re-generating videos with different random seeds. Recent techniques address this issue by fine-tuning a pre-trained model to follow conditioning signals, such as bounding boxes or point trajectories. Yet, this fine-tuning procedure can be computationally expensive, and it requires datasets with annotated object motion, which can be difficult to procure. In this work, we introduce SG-I2V, a framework for controllable image-to-video generation that is self-guided$\unicode{x2013}$offering zero-shot control by relying solely on the knowledge present in a pre-trained image-to-video diffusion model without the need for fine-tuning or external knowledge. Our zero-shot method outperforms unsupervised baselines while significantly narrowing down the performance gap with supervised models in terms of visual quality and motion fidelity. Additional details and video results are available on our project page: https://kmcode1.github.io/Projects/SG-I2V
title SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2411.04989