跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-18AI 評分31

Holo4D:以幾何控制影片擴散的整體式 4D 重建

Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion

AI 導讀

Holo4D 以重建的 3D 軌跡構成整體式 4D 支架,引導影片擴散模型生成新視角影片,同時保留場景幾何結構與動態。實驗展示以軌跡作為條件對鏡頭控制和新視角合成的價值;框架可配合不同的 4D 重建器,無須重新訓練影片生成器。

正文

Published on Oct 18

Authors:

,

,

,

,

Abstract

Holo4D guides video diffusion with reconstructed 3D trajectory scaffolds to synthesize novel-view videos while preserving geometry and motion.

Synthesizing a monocular video from a new camera trajectory requires preserving the observed scene geometry and motion while completing regions that become newly visible. Feed-forward 4D reconstructors recover the structure of the observed scene, whereas video diffusion models provide a generative prior for completing unseen content. We introduce Holo4D, a video reshooting framework that uses reconstructed 3D trajectories as a holistic source-view 4D scaffold. We project these trajectories into the requested views and encode their geometry and source appearance to guide a pretrained video diffusion model. Together with the source video and target cameras, the scaffold grounds generation in reconstructed observations while leaving unsupported regions to the generative prior. Experiments demonstrate the value of trajectory-based conditioning for camera control and novel-view synthesis. The framework accommodates different 4D reconstructors without retraining the video generator, allowing it to benefit from future advances in source reconstruction. More details can be found in our project page.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.25276

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.25276 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.25276 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.25276 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co