UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models
Paper • 2608.04701 • Published • 7
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image, export_to_video
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Drexubery/UniView", dtype=torch.bfloat16, device_map="cuda")
pipe.to("cuda")
prompt = "A man with short gray hair plays a red electric guitar."
image = load_image(
"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png"
)
output = pipe(image=image, prompt=prompt).frames[0]
export_to_video(output, "output.mp4")UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models
UniWorld-View is a unified framework for controllable large-baseline novel view synthesis from monocular inputs (casual videos or single images) using video diffusion models.
- Paper: UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models
- Project Page: https://zhouhyocean.github.io/uniworld-view/
- GitHub Repository: https://github.com/PKU-YuanGroup/UniWorld-View
Citation
@misc{zhou2026uniworldviewlargebaselineviewsynthesis,
title={UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models},
author={Haiyang Zhou and Wangbo Yu and Chaoran Feng and Xunyu Zhou and Yonghong Tian and Li Yuan},
year={2026},
eprint={2608.04701},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2608.04701},
}
- Downloads last month
- 564