ProMist-5K: A Comprehensive Dataset for Digital Emulation of Cinematic Pro-Mist Filter Effects

TL;DR

ProMist-5K is a high-resolution dataset designed to digitally emulate cinematic pro-mist filter effects, capturing realistic glow and diffusion for improved style transfer in film-inspired imagery.

Contribution

It introduces a physically inspired, scene-referred dataset with 20,000 image pairs focused on realistic diffusion effects for cinematic style emulation.

Findings

Dataset effectively supports various image translation models.

Captures both subtle and strong cinematic diffusion effects.

Enhances digital reproduction of traditional lens aesthetics.

Abstract

Pro-Mist filters are widely used in cinematography for their ability to create soft halation, lower contrast, and produce a distinctive, atmospheric style. These effects are difficult to reproduce digitally due to the complex behavior of light diffusion. We present ProMist-5K, a dataset designed to support cinematic style emulation. It is built using a physically inspired pipeline in a scene-referred linear space and includes 20,000 high-resolution image pairs across four configurations, covering two filter densities (1/2 and 1/8) and two focal lengths (20mm and 50mm). Unlike general style datasets, ProMist-5K focuses on realistic glow and highlight diffusion effects. Multiple blur layers and carefully tuned weighting are used to model the varying intensity and spread of optical diffusion. The dataset provides a consistent and controllable target domain that supports various image translation models and learning paradigms. Experiments show that the dataset works well across different training settings and helps capture both subtle and strong cinematic appearances. ProMist-5K offers a practical and physically grounded resource for film-inspired image transformation, bridging the gap between digital flexibility and traditional lens aesthetics. The dataset is available at https://www.kaggle.com/datasets/yingtielei/promist5k.