ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuning

TL;DR

ReCapture enables the creation of new, visually coherent videos with different camera angles and motions from a single user-provided video, using a novel fine-tuning approach and scene hallucination.

Contribution

It introduces a method to generate diverse camera trajectories and hallucinate unseen scene parts from a single video using masked video fine-tuning.

Findings

Successfully re-angled videos with consistent scene motion

Plausibly hallucinated unseen scene regions

Generated diverse cinematic camera motions

Abstract

Recently, breakthroughs in video modeling have allowed for controllable camera trajectories in generated videos. However, these methods cannot be directly applied to user-provided videos that are not generated by a video model. In this paper, we present ReCapture, a method for generating new videos with novel camera trajectories from a single user-provided video. Our method allows us to re-generate the reference video, with all its existing scene motion, from vastly different angles and with cinematic camera motion. Notably, using our method we can also plausibly hallucinate parts of the scene that were not observable in the reference video. Our method works by (1) generating a noisy anchor video with a new camera trajectory using multiview diffusion models or depth-based point cloud rendering and then (2) regenerating the anchor video into a clean and temporally consistent reangled video using our proposed masked video fine-tuning technique.