LowPowAR: Power-Constrained Tone Mapping for Augmented Reality

TVCG 2026 (ISMAR Journal Track)
1 University of Rochester 2 Meta

Overview

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.

LowPowAR teaser showing optical see-through augmented-reality image formation and comparisons with uniform dimming at 40 and 80 percent power savings.

Teaser Video

Image Examples

Visual comparisons against baselines across different power budgets and foreground-to-background luminance ratios. The annotated throughput was measured on an NVIDIA Jetson Xavier AGX.

Video Examples

LowPowAR can be applied to dynamic content and runs in real time. These examples span communication, social media, video playback, and browsing tasks.

FaceTime Memoji
TikTok iOS Scroll
TikTok Video Slide
TikTok Web Browse
Twitch Browse
YouTube 4K Search
YouTube Home