Paper page - 4DAnyone: Create Anyone in 4D from a Casual Monocular Video

Source: https://huggingface.co/papers/2608.20335

Abstract

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 overcome scaling bottlenecks.

We present 4DAnyone, a framework for reconstructing 4D humans from an uncalibrated monocular video by generating reconstruction-grade multiview-consistent videos and lifting them into4D Gaussian Splatting(4DGS). Existing camera-controlledvideo diffusion modelssynthesize plausible novel-view videos but fail to maintain consistency when scaled to the tens of target views required for 4DGS reconstruction. We identify this failure as abounded-attention-contextproblem: when target views exceed the capacity of a singleDiTforward pass, they must be split into groups, exposing two coupled bottlenecks. On the reference-context side, conditioning on all previously generated views grows as O(N), weakening cross-view appearance guidance. On the target-context side, disjoint groups cannot directly exchange information, causing global structural drift. 4DAnyone addresses both bottlenecks with two complementary designs:Reference Context Packing(RCP) compresses growing reference views into a fixed-length mixed-resolution context with O(1) reference-context complexity, whileTarget Context Routing(TCR) rotates target-view groupings during denoising to share context across groups at high-noise steps and stabilize details at low-noise steps. We further build the MVGameHuman dataset using our in-house game engine and combine it with light-stage and in-the-wild video datasets for training. Experiments on DNA-Rendering and DyMVHumans show that 4DAnyone outperforms prior methods in both novel-view video quality and downstream 4DGS reconstruction, with robust in-the-wild generalization. See our project page for video results and source code: https://4danyone.github.io.

View arXiv pageView PDFProject pageGitHub20Add to collection

Get this paper in your agent:

hf papers read 2608\.20335

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### AntResearch/4DAnyone Video-to-Video• Updatedabout 1 hour ago • 1

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.20335 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.20335 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.