Skip to content
AI News HubLIVE
Original source2 min read

Infer3D: Inverse Generative Modeling Enables Robust 3D Reconstruction

Summary

arXiv paper Infer3D introduces an inverse generative modeling framework that recovers latent variables of a generative model to match monocular input, coupled with a frozen 3D lifting network to constrain optimization to a valid manifold. It achieves superior out-of-distribution reconstruction accuracy compared to feedforward networks and uses adaptive inference to allocate more test-time compute to ambiguous examples.

SourcearXiv Computer VisionAuthor: Amani Kiruga, Mark Hamilton, Joshua B. Tenenbaum, William T. Freeman, Vincent Sitzmann, Yilun Du, Ayush Tewari
Infer3D: Inverse Generative Modeling Enables Robust 3D Reconstruction
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 18 Nov 2026]

Title:Infer3D: Inverse Generative Modeling Enables Robust 3D Reconstruction

View a PDF of the paper titled Infer3D: Inverse Generative Modeling Enables Robust 3D Reconstruction, by Amani Kiruga and 6 other authors

View PDF HTML (experimental)

Abstract:Humans can understand the 3D structure of scenes even from highly unfamiliar or extreme viewpoints. Cognitive science suggests this generalization stems from a top-down generative inference strategy. In contrast, state-of-the-art 3D reconstruction neural networks typically rely on amortized, feedforward inference. While fast, this pattern-matching approach degrades when faced with out-of-distribution (OOD) scene conditions unseen during training. Inspired by the generative nature of human vision, we propose Infer3D, an inverse generative modeling framework that recovers the latent variables of a generative model to best match the monocular input. To prevent degenerate flat outputs, we couple the generative image prior with a frozen 3D lifting network that constrains the optimization space to a valid, multi-view-consistent 3D manifold. Across a variety of controlled synthetic and real-world tasks, Infer3D demonstrates superior OOD reconstruction accuracy compared to feedforward networks trained on equal or larger datasets. Furthermore, mirroring how human perception requires more time to process confusing stimuli, we introduce an adaptive inference strategy that expends more test-time compute on ambiguous OOD examples while efficiently routing in-distribution inputs. Project website: this https URL

Comments: 23 pages, 12 figures, 15 tables. Includes references and appendices. Project page: this https URL

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Robotics (cs.RO)

Cite as: arXiv:2611.25061 [cs.CV]

(or arXiv:2611.25061v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.25061

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Amani Kiruga [view email] [v1] Wed, 18 Nov 2026 19:07:33 UTC (8,106 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Infer3D: Inverse Generative Modeling Enables Robust 3D Reconstruction, by Amani Kiruga and 6 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 cs.LG cs.RO

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

  • Infer3D is inspired by top-down generative inference in human vision and replaces amortized feedforward inference with inverse generative modeling.
  • The method couples a generative image prior with a frozen 3D lifting network to avoid degenerate flat outputs and maintain multi-view consistency.
  • Across synthetic and real-world tasks, Infer3D outperforms feedforward networks trained on equal or larger datasets on out-of-distribution reconstruction.
  • An adaptive inference strategy expends more test-time compute on ambiguous OOD examples while efficiently routing in-distribution inputs.

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