Position: Agentic Systems Constitute a Key Component of Next-Generation Intelligent Image Processing

TL;DR

This paper advocates for integrating agentic system design into image processing to enhance adaptability and problem-solving, moving beyond traditional model-centric approaches.

Contribution

It introduces the concept of agentic image processing systems, outlining their design principles and potential to address current limitations in the field.

Findings

Agentic systems can dynamically select and optimize image processing tools.

Such systems emulate human strategic tool orchestration.

They offer improved generalization and flexibility over traditional models.

Abstract

This position paper argues that the image processing community should broaden its focus from purely model-centric development to include agentic system design as an essential complementary paradigm. While deep learning has significantly advanced capabilities for specific image processing tasks, current approaches face critical limitations in generalization, adaptability, and real-world problem-solving flexibility. We propose that developing intelligent agentic systems, capable of dynamically selecting, combining, and optimizing existing image processing tools, represents the next evolutionary step for the field. Such systems would emulate human experts' ability to strategically orchestrate different tools to solve complex problems, overcoming the brittleness of monolithic models. The paper analyzes key limitations of model-centric paradigms, establishes design principles for agentic image processing systems, and outlines different capability levels for such agents.