LowPowAR: Power-Constrained Tone Mapping for Augmented Reality

2026-07-21

AI Summary

This work addresses the challenge of maintaining high-quality visual experience in wearable augmented reality (AR) glasses under stringent power constraints. The authors formulate display power optimization as a tone mapping problem under a fixed power budget and propose an end-to-end learning framework grounded in human visual perception to maximize perceptual quality given limited energy. Key innovations include a differentiable, optimization-friendly parameterization of the tone mapping operator, a progressive optimization strategy, and the distillation of the iterative optimization process into a lightweight feedforward network to achieve both high performance and real-time operation. Subjective evaluations demonstrate that the proposed method significantly outperforms existing approaches at the same power consumption, yielding substantially improved perceptual visual quality.

Abstract

Everyday-wearable Augmented Reality (AR) glasses must meet strict power limits, making displays a key target for optimization. We cast display power optimization as a power-constrained tone-mapping problem and propose a human-vision-grounded, learning-based framework that maximizes perceptual quality under a given power budget. We introduce an optimization-friendly tone-mapping operator (TMO) parameterization along with a progressive optimization strategy to effectively navigate the quality-vs-power landscape. We distill the iterative optimization into a lightweight feed-forward neural network for real-time deployment. Subjective experiments show that our method yields better perceptual quality than prior work at the same power budget. Project page: https://horizon-lab.org/lowpowar/.

Problem

• Augmented Reality
• Tone Mapping
• Power Constraint
• Perceptual Quality
• Wearable Display

Innovation

• power-constrained tone mapping
• human-vision-grounded optimization
• lightweight neural network
• perceptual quality
• AR display power efficiency