How Much Does Saliency Accuracy Matter for Saliency-Guided 360-degree Image Compression?

Saliency-guided coding allocates bits to the regions viewers are most likely to attend, but accurate 360-degree saliency prediction is computationally expensive, an obstacle for low-latency immersive streaming applications such as robot teleoperation. We quantify how much saliency-prediction accuracy actually translates into compression gain. Building on a saliency-guided rate-distortion-optimized (RDO) learned codec, modified so that the training-time latent mask is driven by ground-truth saliency, which yields a single, predictor-agnostic codec, we evaluate saliency predictors spanning two orders of magnitude in compute on both the learned codec and H.265/HEVC. The results show that higher saliency-prediction accuracy yields diminishing compression gains: a lightweight predictor fast enough for live use (52 frames per second) captures 65% of the ground-truth oracle's bit-rate saving, a 3.3x heavier one reaches 74%, and a further 38x increase in compute adds no measurable benefit, on either codec. Therefore, lightweight predictors might also be a practical choice for latency-constrained 360-degree streaming.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.21532
Primary Topic
Video Coding and Compression Technologies
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

How Much Does Saliency Accuracy Matter for Saliency-Guided 360-degree Image Compression?

Guillaume Caron, Philippe Brunet, Nevrez İmamoğlu, Sidi-Mohammed Senouci et al.
arXiv (Cornell University)
Video Coding and Compression Technologies
preprint

How Much Does Saliency Accuracy Matter for Saliency-Guided 360-degree Image Compression?

Guillaume Caron, Philippe Brunet, Nevrez İmamoğlu, Sidi-Mohammed Senouci, Sakib Ahmed
preprint en

Abstract

Saliency-guided coding allocates bits to the regions viewers are most likely to attend, but accurate 360-degree saliency prediction is computationally expensive, an obstacle for low-latency immersive streaming applications such as robot teleoperation. We quantify how much saliency-prediction accuracy actually translates into compression gain. Building on a saliency-guided rate-distortion-optimized (RDO) learned codec, modified so that the training-time latent mask is driven by ground-truth saliency, which yields a single, predictor-agnostic codec, we evaluate saliency predictors spanning two orders of magnitude in compute on both the learned codec and H.265/HEVC. The results show that higher saliency-prediction accuracy yields diminishing compression gains: a lightweight predictor fast enough for live use (52 frames per second) captures 65% of the ground-truth oracle's bit-rate saving, a 3.3x heavier one reaches 74%, and a further 38x increase in compute adds no measurable benefit, on either codec. Therefore, lightweight predictors might also be a practical choice for latency-constrained 360-degree streaming.

arXiv (Cornell University)
Video Coding and Compression Technologies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon