Hierarchical Masked 3D Diffusion Model for Video Outpainting

TL;DR

This paper introduces a hierarchical masked 3D diffusion model for video outpainting that maintains temporal consistency and reduces artifacts, achieving state-of-the-art results in filling missing video frame areas.

Contribution

The paper proposes a novel masked 3D diffusion approach with hybrid coarse-to-fine inference and cross-attention guidance for improved video outpainting.

Findings

Achieves state-of-the-art performance on video outpainting benchmarks.

Effectively maintains temporal consistency across frames.

Reduces artifacts with hybrid infilling and interpolation strategies.

Abstract

Video outpainting aims to adequately complete missing areas at the edges of video frames. Compared to image outpainting, it presents an additional challenge as the model should maintain the temporal consistency of the filled area. In this paper, we introduce a masked 3D diffusion model for video outpainting. We use the technique of mask modeling to train the 3D diffusion model. This allows us to use multiple guide frames to connect the results of multiple video clip inferences, thus ensuring temporal consistency and reducing jitter between adjacent frames. Meanwhile, we extract the global frames of the video as prompts and guide the model to obtain information other than the current video clip using cross-attention. We also introduce a hybrid coarse-to-fine inference pipeline to alleviate the artifact accumulation problem. The existing coarse-to-fine pipeline only uses the infilling strategy, which brings degradation because the time interval of the sparse frames is too large. Our pipeline benefits from bidirectional learning of the mask modeling and thus can employ a hybrid strategy of infilling and interpolation when generating sparse frames. Experiments show that our method achieves state-of-the-art results in video outpainting tasks. More results and codes are provided at our https://fanfanda.github.io/M3DDM/.