CVGROct 17, 2024

VidPanos: Generative Panoramic Videos from Casual Panning Videos

arXiv:2410.13832v211 citationsh-index: 33SIGGRAPH Asia
Originality Highly original
AI Analysis

This addresses the challenge of capturing dynamic scenes in wide-angle views for applications like video editing or immersive media, representing a novel extension beyond static panorama stitching.

The paper tackles the problem of generating panoramic videos from casual panning videos, especially in scenes with moving objects, by posing it as a space-time outpainting problem and adapting generative video models to create consistent, realistic panoramas.

Panoramic image stitching provides a unified, wide-angle view of a scene that extends beyond the camera's field of view. Stitching frames of a panning video into a panoramic photograph is a well-understood problem for stationary scenes, but when objects are moving, a still panorama cannot capture the scene. We present a method for synthesizing a panoramic video from a casually-captured panning video, as if the original video were captured with a wide-angle camera. We pose panorama synthesis as a space-time outpainting problem, where we aim to create a full panoramic video of the same length as the input video. Consistent completion of the space-time volume requires a powerful, realistic prior over video content and motion, for which we adapt generative video models. Existing generative models do not, however, immediately extend to panorama completion, as we show. We instead apply video generation as a component of our panorama synthesis system, and demonstrate how to exploit the strengths of the models while minimizing their limitations. Our system can create video panoramas for a range of in-the-wild scenes including people, vehicles, and flowing water, as well as stationary background features.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes