Form and Void: Entangled Composition through an Autonomous AI Agent

arXiv:2610.02045 · cs.CV, cs.MA · Submitted 2026-10-01 · Read on arXiv

cs.CV, cs.MA

Submitted: 2026-10-01

Updated: 2026-10-02

Comments: CVPR Workshops AI4VA, 2026, Best Paper Award

Journal ref: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026, pp. 8987-8995

License: http://creativecommons.org/licenses/by/4.0/

The gist: Positive and negative space is a fundamental principle in visual composition, supporting visually coherent forms and layered semantic relationships.

Terminology

Abstract

Positive and negative space is a fundamental principle in visual composition, supporting visually coherent forms and layered semantic relationships. Generating such compositions is challenging because it requires coordinated control over two semantic concepts that share a common boundary. Although recent text-to-image models and multimodal large language models (MLLMs) have achieved strong performance in image generation and visual understanding, positive-negative space generation remains difficult, particularly under direct single-pass prompting. In this work, we present the Form and Void Agent (FaV-A), a multimodal agent designed for staged positive-negative space generation. FaV-A follows a progressive workflow: it first generates a base object, then analyzes its shape and spatial structure to identify candidate negative-space semantics, and finally produces compositional instructions for the final image generation stage. Experimental results and ablation analyses suggest that FaV-A provides a more effective framework than direct zero-shot MLLM baselines for producing visually coherent and semantically aligned positive-negative space compositions.

Sources

Related papers