Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
Summary
Holo4D is a video reshooting framework that uses reconstructed 3D trajectory scaffolds to guide a pretrained video diffusion model for novel-view video synthesis, preserving scene geometry and motion while generatively completing unseen regions without retraining the generator.
View Cached Full Text
Cached at: 10/30/26, 03:14 PM
Paper page - Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
Source: https://huggingface.co/papers/2610.25276
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-forward4D reconstructorsrecover the structure of the observed scene, whereasvideo diffusion modelsprovide a generative prior for completing unseen content. We introduce Holo4D, a video reshooting framework that uses reconstructed3D trajectoriesas a holistic source-view4D 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 oftrajectory-based conditioningfor camera control andnovel-view synthesis. The framework accommodates different4D reconstructorswithout 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 pageView PDFProject pageGitHub17Add 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 paper0
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 paper0
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 paper0
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 paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
4DAnyone: Create Anyone in 4D from a Casual Monocular Video
4DAnyone reconstructs 4D humans from monocular video by generating multiview-consistent videos and lifting them into 4D Gaussian Splatting, using reference and target context designs to address scaling bottlenecks.
Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild
Lift4D is a test-time optimization framework that reconstructs complete 4D geometry, appearance, and deformation of dynamic objects from a single monocular in-the-wild video, improving over prior methods on challenging sequences with occlusions and non-rigid motion.
Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video Diffusion
Pantheon360 introduces a 3D-aware 360° video diffusion framework that uses an explicit 3D cache to enforce geometric consistency, enabling high-fidelity digital twin generation from sparse 360° inputs.
Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models
Stream4D enhances streaming autoregressive diffusion video models by introducing a dynamic 4D reconstruction reward and motion prior to maintain coherent motion and reduce geometric drift.
Helix4D: Complex 4D Mesh Generation
Helix4D introduces a framework for high-quality dynamic 4D mesh generation from video by extending Trellis2 with cross-frame attention and a 4D temporal encoding that repurposes redundant spatial RoPE bands without adding parameters.