Structural Regularities of Cinema SDR-to-HDR Mapping in a Controlled Mastering Workflow: A Pixel-wise Case Study on ASC StEM2

2026-04-07

AI Summary

This study investigates the pixel-level structural mapping between SDR and HDR versions of cinematic content produced under a unified mastering workflow. Leveraging 18,580 frames from the ASC StEM2 dataset, the research conducts a tri-domain comparison among EXR source, SDR, and HDR representations, integrating luminance–chrominance dimensional modeling with pixel-level statistical analysis. For the first time within a common-source controlled pipeline, it quantitatively reveals the structural regularities governing SDR–HDR mapping. Key findings include a stable monotonic relationship in luminance; chroma saturation exhibiting shadow suppression, midtone expansion, and highlight convergence; and 82.4% of pixels falling into an EXR-proximal recovery region. Based on these observations, an interpretable pixel-level decision map is constructed to delineate regions amenable to direct recovery versus those requiring adaptive adjustment.

Abstract

We present an empirical case study of cinema SDR-to-HDR mapping using ASC StEM2, a rare common-source dataset containing EXR scene-referred images and matched SDR/HDR cinema release masters from the same ACES-based mastering workflow. Based on pixel-wise statistics over all 18,580 frames of the test film, we construct a three-domain comparison involving EXR source data, SDR release masters, and HDR release masters to characterize their luminance and color structural relationships within this controlled workflow. In the luminance dimension, SDR and HDR masters exhibit a highly stable global monotonic correspondence, with geometric structure remaining largely consistent overall; sparse and structured deviations appear in self-luminous highlights and specific material regions. In the color dimension, the two masters remain largely consistent in hue, with saturation exhibiting a redistribution pattern of shadow suppression, midtone expansion, and highlight convergence. Using EXR as a scene-referred anchor, we further define a pixel-level decision map that operationally separates EXR-closer recovery regions from content-adaptive adjustment regions. Under this operational definition, 82.4% of sampled image regions are classified as EXR-closer recovery, while the remainder require localized adaptive adjustment. Rather than claiming a universal law for all cinema mastering pipelines, the study provides an interpretable quantitative baseline for structure-aware SDR-to-HDR analysis and for designing learning-based models under shared-source mastering conditions.

Problem

• SDR-to-HDR mapping
• structural regularities
• cinema mastering
• pixel-wise analysis
• scene-referred imaging

Innovation

• SDR-to-HDR mapping
• scene-referred imaging
• pixel-wise analysis
• structural regularity
• ACES workflow