Paper Detail

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

Yushi Lan, Zeren Jiang, Koichi Namekata, Xingang Pan, Chuanxia Zheng, Andrea Vedaldi

huggingface Score 4.5

Published 2026-10-18 · First seen 2026-10-30

General AI

Abstract

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{lan2026holo4d,
  title = {Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion},
  author = {Yushi Lan and Zeren Jiang and Koichi Namekata and Xingang Pan and Chuanxia Zheng and Andrea Vedaldi},
  year = {2026},
  abstract = {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 },
  url = {https://huggingface.co/papers/2610.25276},
  keywords = {4D reconstructors, video diffusion models, 3D trajectories, 4D scaffold, trajectory-based conditioning, novel-view synthesis, code available, huggingface daily},
  eprint = {2610.25276},
  archiveprefix = {arXiv},
}

Metadata

{}