Semantically Consistent Video Inpainting with Conditional Diffusion Models

Dylan Green, William Harvey, Saeid Naderiparizi, Matthew Niedoba, Yunpeng Liu, Xiaoxuan Liang, Jonathan Wilder Lavington, Ke Zhang, Vasileios Lioutas, Setareh Dabiri, Adam Scibior, Berend Zwartsenberg, Frank Wood

Keywords: diffusion models, video inpainting, conditional generative modeling

TL;DR: Conditional video diffusion models are capable of solving challenging video inpainting tasks where current state-of-the-art video inpainting methods struggle.

Abstract: Current state-of-the-art methods for video inpainting typically rely on optical flow or attention-based approaches to inpaint masked regions by propagating visual information across frames. While such approaches have led to significant progress on standard benchmarks, they struggle with tasks that require the synthesis of novel content that is not present in other frames. In this paper, we reframe video inpainting as a conditional generative modeling problem and present a framework for solving such problems with conditional video diffusion models. We introduce inpainting-specific sampling schemes which capture crucial long-range dependencies in the context, and devise a novel method for conditioning on the known pixels in incomplete frames. We highlight the advantages of using a generative approach for this task, showing that our method is capable of generating diverse, high-quality inpaintings and synthesizing new content that is spatially, temporally, and semantically consistent with the provided context.

Primary Area: applications to computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1967