Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting

TL;DR

This paper introduces Reshoot-Anything, a self-supervised framework that leverages internet-scale monocular videos to enable high-quality, temporally consistent video reshooting and novel view synthesis without requiring paired multi-view data.

Contribution

The authors propose a scalable self-supervised method that generates pseudo multi-view training triplets from monocular videos, improving dynamic scene reshooting capabilities.

Findings

Achieves state-of-the-art temporal consistency in dynamic scene reshooting.

Effectively reconstructs high-fidelity novel views from monocular videos.

Demonstrates robustness across complex non-rigid scenes.

Abstract

Precise camera control for reshooting dynamic videos is bottlenecked by the severe scarcity of paired multi-view data for non-rigid scenes. We overcome this limitation with a highly scalable self-supervised framework capable of leveraging internet-scale monocular videos. Our core contribution is the generation of pseudo multi-view training triplets, consisting of a source video, a geometric anchor, and a target video. We achieve this by extracting distinct smooth random-walk crop trajectories from a single input video to serve as the source and target views. The anchor is synthetically generated by forward-warping the first frame of the source with a dense tracking field, which effectively simulates the distorted point-cloud inputs expected at inference. Because our independent cropping strategy introduces spatial misalignment and artificial occlusions, the model cannot simply copy information from the current source frame. Instead, it is forced to implicitly learn 4D spatiotemporal structures by actively routing and re-projecting missing high-fidelity textures across distinct times and viewpoints from the source video to reconstruct the target. At inference, our minimally adapted diffusion transformer utilizes a 4D point-cloud derived anchor to achieve state-of-the-art temporal consistency, robust camera control, and high-fidelity novel view synthesis on complex dynamic scenes.