We present TrajectoryCrafter, a novel approach to redirect camera trajectories for monocular videos. By disentangling deterministic view transformations from stochastic content generation, our method achieves precise control over user-specified camera trajectories. We propose a novel dual-stream conditional video diffusion model that concurrently integrates point cloud renders and source videos as conditions, ensuring accurate view transformations and coherent 4D content generation. Instead of leveraging scarce multi-view videos, we curate a hybrid training dataset combining web-scale monocular videos with static multi-view datasets, by our innovative double-reprojection strategy, significantly fostering robust generalization across diverse scenes. Extensive evaluations on multi-view and large-scale monocular videos demonstrate the superior performance of our method.
View on arXiv@article{yu2025_2503.05638,
title={ TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models },
author={ Mark YU and Wenbo Hu and Jinbo Xing and Ying Shan },
journal={arXiv preprint arXiv:2503.05638},
year={ 2025 }
}