Skip to content
AI News HubLIVE
Original source2 min read

Do Deep Stereo Models Learn Shape Priors?

Summary

A new study investigates whether deep stereo models produce boundaries consistent with simple shape priors when local cues are weak. Using a synthetic dataset of constrained shapes, researchers find systematic boundary errors in state-of-the-art models and propose a generative model that jointly predicts disparity and a distance field to improve boundary localization.

SourcearXiv Computer VisionAuthor: Linbo Tang, Aneel Damaraju, Todd Zickler
Do Deep Stereo Models Learn Shape Priors?
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:Do Deep Stereo Models Learn Shape Priors?

View a PDF of the paper titled Do Deep Stereo Models Learn Shape Priors?, by Linbo Tang and 2 other authors

View PDF HTML (experimental)

Abstract:Localizing object boundaries is important for embodied visual systems, since small boundary errors can change the inferred geometry of physical surfaces. We study whether deep stereo models produce boundaries consistent with simple shape priors when local image and disparity cues are weak. We create a synthetic stereo dataset consisting of objects drawn from a highly constrained family of shapes, with randomized depth, slant, color and texture. Despite the simplicity of this shape space, we find that several state-of-the-art stereo models retain systematic boundary errors, even when finetuned or trained from scratch on the dataset. We then introduce a simple generative stereo model that jointly predicts disparity and a distance field representing object boundaries. The model improves boundary localization and produces contours that adhere more closely to the underlying shape space. These results expose limitations in the boundary predictions of current stereo architectures when local evidence is weak, and motivate further study of whether generative models can better combine regional grouping evidence with global geometric structure.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2611.25113 [cs.CV]

(or arXiv:2611.25113v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.25113

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Linbo Tang [view email] [v1] Wed, 18 Nov 2026 19:51:54 UTC (9,757 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Do Deep Stereo Models Learn Shape Priors?, by Linbo Tang and 2 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

  • Several state-of-the-art stereo models retain systematic boundary errors on a highly constrained shape space.
  • These errors persist even when models are finetuned or trained from scratch on the dataset.
  • A generative stereo model that jointly predicts disparity and a distance field for object boundaries improves boundary localization and produces contours closer to the underlying shape space.
  • The results expose limitations of current stereo architectures when local evidence is weak and motivate further study of generative models for combining regional grouping with global geometric structure.

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

Do Deep Stereo Models Learn Shape Priors? | AI News Hub