Skip to content
AI News HubLIVE
Original source3 min read

Every Camera Grows Up: Camera-Height Regression in Interactive Video World Models

Summary

Six recent open-weight interactive video world models fail to maintain the camera height set by the starting image, drifting toward human eye level as motion replaces the initial view. The EyeHeight benchmark reveals this camera-height regression, traces it to human-centric video priors, and shows that viewpoint drift alone can shift visual navigation policy predictions.

SourcearXiv Computer VisionAuthor: Sheng Lu, Guangpin Tao, Tong Lu, Ying Tai
Every Camera Grows Up: Camera-Height Regression in Interactive Video World Models
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 16 Nov 2026]

Title:Every Camera Grows Up: Camera-Height Regression in Interactive Video World Models

View a PDF of the paper titled Every Camera Grows Up: Camera-Height Regression in Interactive Video World Models, by Sheng Lu and 3 other authors

View PDF HTML (experimental)

Abstract:Interactive video world models serve as simulators for embodied agents: from a starting image and an action trajectory, they generate the views the agent would see. The starting image fixes how high the camera is, for example 0.15 m for a floor robot or 2.2 m for an overhead camera, and a faithful simulator must keep this height as the camera moves. We show that six recent open-weight models fail to do so: as motion replaces the starting view with generated content, they move the camera toward human eye level, a failure we call camera-height regression. Our benchmark, EyeHeight, pairs six rendered elevations (0.15 m to 2.2 m) and four calibrated real-world rig heights with scale-free multi-view height estimation. All six models lose their initial height during a $180^\circ$ turn-and-walk rollout: initialized at 0.15 m, only 0-20% of clips end within $1.3\times$ of the starting height as inferred viewpoints converge to human heights of 1.1 m to 1.5 m, whereas ground-truth renders remain within a few percent. In Matrix-Game models, homography-tracked floor motion stays consistent with constant elevation during rotation even as newly outpainted room geometry yields a higher reconstructed viewpoint. Regression grows with rotation angle, begins while the start frame remains in context, and largely reverses in SANA-WM when a $360^\circ$ turn restores the initial view. We trace this pull to human-centric video priors in which floor-level views are nearly absent: in SANA-WM, textual height cues and dense floor-disparity maps do not prevent it, whereas classifier-free text guidance during the first half of denoising strengthens it. Combining unguided sampling with height-balanced fine-tuning recovers more retention but costs 5 MUSIQ points, a loss fixed during those same early steps. Viewpoint drift alone shifts the paths predicted by visual navigation policies.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2611.21782 [cs.CV]

(or arXiv:2611.21782v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.21782

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Guangpin Tao [view email] [v1] Mon, 16 Nov 2026 19:07:01 UTC (2,761 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Every Camera Grows Up: Camera-Height Regression in Interactive Video World Models, by Sheng Lu and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • All six open-weight models lose initial camera height during 180° turn-and-walk rollouts; at 0.15 m start only 0–20% of clips end within 1.3× of the starting height.
  • Regression grows with rotation angle, begins while the start frame remains in context, and largely reverses in SANA-WM after a 360° turn restores the initial view.
  • The pull stems from human-centric video priors with almost no floor-level views; unguided sampling plus height-balanced fine-tuning helps but costs 5 MUSIQ points.
  • Viewpoint drift alone shifts visual navigation policy paths, undermining the use of these models as embodied-agent simulators.

Highlights and analysis are generated automatically and may contain errors. Check the original source.