Work

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

Year: 2026

Type: conference-paper

Abstract: Selection is a core operation in interactive image editing, enabling tasks such as composition or manipulation. To be practically useful, 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 can be particularly valuable for tasks like re-texturing surfaces or consistently editing all instances of a specific material in a scene. However, existing vision–language-model (VLM) based selection methods are largely object-centric and typically support only a single interaction modality, limiting their applicability in real editing workflows.

Source: ACM SIGGRAPH Conference Papers (SIGGRAPH)

DOI: 10.1145/3799902.3811186

Authors: Jaden Park, Valentin Deschaintre, Jason Kuen, Kangning Liu, Iliyan Georgiev, Krishna Kumar Singh, Yong Jae Lee, Michael Fischer

Institutions: University of Wisconsin–Madison, Adobe Systems (United States)

Topic: Generative Adversarial Networks and Image Synthesis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7163695008

FWCI:

Cites:

Cited by:

Related to: