Skip to content
AI News HubLIVE
Original source2 min read

Where Appearance Fails, Geometry Recognizes: A CAD-Free 3D Shape Prior That Complements Vision Foundation Models

Summary

For object recognition without labeled training sets or CAD models, this paper proposes a short object-centric scan reconstructed via 3D Gaussian Splatting, summarized into a per-class shape prototype, and fused with frozen DINOv2 features. Geometry alone reaches 0.920 on HOPE versus 0.832 image-only; on T-LESS fusion lifts 0.560-class single signals to 0.591. Rendered pixels add no value, and the prior mainly saves image failures, especially under occlusion.

SourcearXiv Computer VisionAuthor: Chenxi Tao, Seung-Kyum Choi
Where Appearance Fails, Geometry Recognizes: A CAD-Free 3D Shape Prior That Complements Vision Foundation 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 3 Sep 2026]

Title:Where Appearance Fails, Geometry Recognizes: A CAD-Free 3D Shape Prior That Complements Vision Foundation Models

View a PDF of the paper titled Where Appearance Fails, Geometry Recognizes: A CAD-Free 3D Shape Prior That Complements Vision Foundation Models, by Chenxi Tao and 1 other authors

View PDF HTML (experimental)

Abstract:Recognizing specific objects onboarded without a labeled training set recurs across manufacturing and service robotics, yet the conventional renderable prior, a computer-aided-design (CAD) model, is often unavailable. Two-dimensional capture supplies no shape prior, and frozen foundation features fail on geometrically similar, low-texture industrial parts. We ask what a short object-centric scan buys for recognition beyond the captured images themselves: each object is reconstructed with 3D Gaussian Splatting (3DGS), summarized into a per-class shape prototype, and fused with frozen DINOv2 image features. First, the scan recovers the recognition value of CAD without CAD: geometry from RGB-D depth (on T-LESS), 3DGS, and CAD gives comparable recognition (tied on HOPE, within 1.6 points on T-LESS); 3DGS is only a convenient route to a point cloud. Second, the payoff is governed by how recognizable the shape is: on shape-distinctive household objects (HOPE) geometry alone reaches 0.920 versus image-only 0.832, a ceiling below which fixed-weight fusion (0.872) sits. On shape-confusable textureless industrial parts (T-LESS) the gain is modest but consistent (0.560 to 0.591 fused, above both single signals). Third, the prior is complementary, not uniformly additive: it rescues far more image failures than it breaks successes, and its benefit grows under partial occlusion. Finally, the worth lies in geometry, not rendered pixels: 3DGS renderings do not help the image side, and frozen-feature recognition is nearly lighting-invariant (within 2.5 points). The study is scoped to recognition, not the BOP pose benchmark.

Comments: 19 pages, 11 figures, 5 tables

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Robotics (cs.RO)

MSC classes: 68T45, 68T07

ACM classes: I.4.8; I.2.10; I.5.4

Cite as: arXiv:2609.04381 [cs.CV]

(or arXiv:2609.04381v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2609.04381

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Chenxi Tao [view email] [v1] Thu, 3 Sep 2026 18:42:59 UTC (7,041 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Where Appearance Fails, Geometry Recognizes: A CAD-Free 3D Shape Prior That Complements Vision Foundation Models, by Chenxi Tao and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-09

Change to browse by:

cs cs.AI cs.RO

References & Citations

NASA ADS

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

  • Reconstructed 3D geometry recovers most of CAD's recognition value: RGB-D depth, 3DGS, and CAD perform comparably on HOPE and within 1.6 points on T-LESS.
  • Fusing frozen DINOv2 features with the shape prototype gives 0.872 on HOPE and 0.591 on T-LESS, above image-only baselines but below the geometry-only ceiling on shape-distinctive objects.
  • The shape prior is complementary: it recovers far more image failures than it breaks, with larger gains under partial occlusion.
  • The benefit comes from geometry, not renderings: 3DGS renderings do not improve image-side recognition, and frozen-feature recognition is nearly lighting-invariant (within 2.5 points).

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

More recent stories on this topic · Models