MAOAM: Unified Object and Material Selection with Vision-Language Models

Hugging Face Daily Papers Papers
vision-language-model object-selection material-selection image-editing segmentation multimodal interactive-editing

Summary

This paper presents MAOAM, a unified vision-language model framework that enables precise object and material selection through text or click interactions for interactive image editing. It introduces a scalable data generation pipeline and shows emergent improvement when combining text and clicks at inference.

Selection is a core operation in interactive image editing. To be practical, a user should be able to specify and disambiguate the desired selection region through either text or click-based interactions, and the system should support selecting not only objects but also other criteria, such as materials. Material-based selection is valuable for tasks like re-texturing surfaces or editing instances of a specific material. However, existing vision-language-model (VLM) based selection methods are object-centric and typically support a single interaction modality, limiting their applicability. In this work, we thus present Mask Any Object And Material (MAOAM), a unified selection framework that enables precise object and material-level selection across both text- and click-based interactions. MAOAM leverages a VLM with a segmentation head to produce pixel-accurate masks from user prompts: the VLM interprets the user's selection intent (object or material-level) and encodes visual entities, attributes, and spatial relations, while the segmentation head decodes the output token into a mask. A key challenge is the lack of material selection datasets with text annotations. We propose a scalable data generation pipeline: we collect real and synthetic images with material masks, and leverage VLMs to generate material descriptions with rich visual-semantics. We train MAOAM with a multi-task objective over click and text-based selection, along with an auxiliary VQA task derived from the material descriptions to facilitate deeper material understanding. Despite being trained with uni-modal prompts, our model exhibits an emergent improvement in selection when combining text and clicks at inference, enabling flexible image editing workflows. Experiments demonstrate accurate and coherent selections across diverse objects, materials, and interaction scenarios, highlighting robustness in practice.
Original Article
View Cached Full Text

Cached at: 06/05/26, 06:09 PM

Paper page - MAOAM: Unified Object and Material Selection with Vision-Language Models

Source: https://huggingface.co/papers/2606.04880

Abstract

A unified vision-language model framework enables precise object and material selection through text or click interactions, supporting diverse editing workflows with improved robustness.

Selection is a core operation in interactive image editing. To be practical, a user should be able to specify and disambiguate the desired selection region through either text or click-based interactions, and the system should support selecting not only objects but also other criteria, such as materials. Material-based selection is valuable for tasks like re-texturing surfaces or editing instances of a specific material. However, existingvision-language-model(VLM) based selection methods are object-centric and typically support a single interaction modality, limiting their applicability. In this work, we thus present Mask Any Object And Material (MAOAM), a unified selection framework that enables precise object and material-level selection across both text- and click-based interactions. MAOAM leverages a VLM with asegmentation headto producepixel-accurate masksfrom user prompts: the VLM interprets the user’s selection intent (object or material-level) and encodesvisual entities, attributes, andspatial relations, while thesegmentation headdecodes the output token into a mask. A key challenge is the lack of material selection datasets with text annotations. We propose a scalable data generation pipeline: we collect real and synthetic images with material masks, and leverage VLMs to generate material descriptions with rich visual-semantics. We train MAOAM with amulti-task objectiveover click and text-based selection, along with an auxiliaryVQA taskderived from the material descriptions to facilitate deeper material understanding. Despite being trained with uni-modal prompts, our model exhibits anemergent improvementin selection when combining text and clicks at inference, enabling flexible image editing workflows. Experiments demonstrate accurate and coherent selections across diverse objects, materials, and interaction scenarios, highlighting robustness in practice.

View arXiv pageView PDFProject pageGitHubAdd to collection

Get this paper in your agent:

hf papers read 2606\.04880

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.04880 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.04880 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.04880 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

LoMo: Local Modality Substitution for Deeper Vision-Language Fusion

Hugging Face Daily Papers

LoMo proposes a data curation method that reformulates single-modality prompts into interleaved multimodal sequences to improve cross-modal representation alignment in vision-language models, achieving consistent gains on multiple benchmarks.