Saved in:
Bibliographic Details
Main Authors: Liu, Yaru, Lemos, Dayllon Vinícius Xavier, Bozorgian, Ali, Zeng, Chengxi, Hepburn, Alexander, Raventos, Arnau
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.07959
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913105875828736
author Liu, Yaru
Lemos, Dayllon Vinícius Xavier
Bozorgian, Ali
Zeng, Chengxi
Hepburn, Alexander
Raventos, Arnau
author_facet Liu, Yaru
Lemos, Dayllon Vinícius Xavier
Bozorgian, Ali
Zeng, Chengxi
Hepburn, Alexander
Raventos, Arnau
contents Many client-side applications, especially games, render video at high resolution and frame rate on power-constrained devices, even when users perceive little or no benefit from all those extra pixels. Existing perceptual video quality metrics can indicate when a lower resolution is "good enough", but they are full-reference and computationally expensive, making them impractical for real-world applications and deployment on-device. In this work, we leverage the spatio-temporal limits of the human visual system and propose a non-reference method that predicts, from the rendered video alone, the lowest resolution that remains perceptually indistinguishable from the best available option, enabling power-efficient client-side rendering. Our approach is codec-agnostic and requires only minimal modifications to existing infrastructure. The network is trained on a large dataset of rendered content labeled with a full-reference perceptual video quality metric. The prediction significantly enhances perceptual quality while substantially reducing computational costs, suggesting a practical path toward perception-guided, power-efficient client-side rendering.
format Preprint
id arxiv_https___arxiv_org_abs_2604_07959
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Seeing enough: non-reference perceptual resolution selection for power-efficient client-side rendering
Liu, Yaru
Lemos, Dayllon Vinícius Xavier
Bozorgian, Ali
Zeng, Chengxi
Hepburn, Alexander
Raventos, Arnau
Graphics
Many client-side applications, especially games, render video at high resolution and frame rate on power-constrained devices, even when users perceive little or no benefit from all those extra pixels. Existing perceptual video quality metrics can indicate when a lower resolution is "good enough", but they are full-reference and computationally expensive, making them impractical for real-world applications and deployment on-device. In this work, we leverage the spatio-temporal limits of the human visual system and propose a non-reference method that predicts, from the rendered video alone, the lowest resolution that remains perceptually indistinguishable from the best available option, enabling power-efficient client-side rendering. Our approach is codec-agnostic and requires only minimal modifications to existing infrastructure. The network is trained on a large dataset of rendered content labeled with a full-reference perceptual video quality metric. The prediction significantly enhances perceptual quality while substantially reducing computational costs, suggesting a practical path toward perception-guided, power-efficient client-side rendering.
title Seeing enough: non-reference perceptual resolution selection for power-efficient client-side rendering
topic Graphics
url https://arxiv.org/abs/2604.07959