Adaptive Dynamic Dehazing via Instruction-Driven and Task-Feedback Closed-Loop Optimization for Diverse Downstream Task Adaptation

TL;DR

This paper introduces an adaptive dehazing framework that uses closed-loop feedback and user instructions to optimize haze removal for diverse downstream vision tasks in real-time.

Contribution

It presents a novel, task-aware dehazing method with feedback and instruction mechanisms enabling real-time adaptation without retraining.

Findings

Effective across multiple vision tasks

Robust and generalizable performance

Enables real-time, user-guided dehazing

Abstract

In real-world vision systems,haze removal is required not only to enhance image visibility but also to meet the specific needs of diverse downstream tasks.To address this challenge,we propose a novel adaptive dynamic dehazing framework that incorporates a closed-loop optimization mechanism.It enables feedback-driven refinement based on downstream task performance and user instruction-guided adjustment during inference,allowing the model to satisfy the specific requirements of multiple downstream tasks without retraining.Technically,our framework integrates two complementary and innovative mechanisms: (1)a task feedback loop that dynamically modulates dehazing outputs based on performance across multiple downstream tasks,and (2) a text instruction interface that allows users to specify high-level task preferences.This dual-guidance strategy enables the model to adapt its dehazing behavior after training,tailoring outputs in real time to the evolving needs of multiple tasks.Extensive experiments across various vision tasks demonstrate the strong effectiveness,robustness,and generalizability of our approach.These results establish a new paradigm for interactive,task-adaptive dehazing that actively collaborates with downstream applications.