Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction
This paper presents a training-free method that leverages pretrained generative image models and vision-language models to extract semantic parts from multi-view images of 3D objects and abstract them into superquadric primitives. The approach contains no learned parameters, is category-agnostic and orientation-invariant, achieving the lowest Chamfer distance on HumanPrim and Toys4K datasets with an average of 5–9 primitives per object. The study shows that the current accuracy bottleneck is part segmentation, not primitive fitting.
-->
[Submitted on 6 Jul 2026]
Title:Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction
View a PDF of the paper titled Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction, by Gregor Kobsik and 2 other authors
View PDF HTML (experimental)
Abstract:Representing 3D shapes as compact sets of geometric primitives is fundamental to robotics, simulation, and scene understanding. Generative image models trained at scale have recently emerged as generalist visual learners that can identify and segment object parts directly in the image domain, across arbitrary categories and without task-specific training. Adapting such models to downstream tasks typically requires fine-tuning; we ask whether their pretrained capability can instead be harnessed directly, without any training, and answer affirmatively with a training-free harness. Our pipeline renders multi-view images of a 3D object, uses a vision-language model to analyze its semantic parts, prompts a generative image model to paint a color-coded part segmentation mask, reprojects it onto the geometry, and fits a superquadric primitive to each part via parameter optimization. The approach contains no learned parameters: it is category-agnostic and orientation-invariant, properties that previous learning-based models struggled with. Its accuracy ceiling rises with future generative-model improvements, which we confirm with a ground-truth segmentation study showing that part segmentation, not primitive fitting, is the current accuracy bottleneck. On HumanPrim and Toys4K, our method achieves the lowest Chamfer distance among all evaluated methods, using 5--9 primitives per object on average.
Comments: 13 pages, 9 figures, 3 tables
Subjects:
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2607.05568 [cs.CV]
(or arXiv:2607.05568v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2607.05568
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Gregor Kobsik [view email] [v1] Mon, 6 Jul 2026 19:10:43 UTC (13,471 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction, by Gregor Kobsik and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-07
Change to browse by:
cs cs.AI
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?)