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

2026-01-27

AI Summary

This work addresses the challenge of accurately simulating the complex optical effects—such as soft focus, reduced contrast, and highlight bloom—produced by Pro-Mist filters in cinematic photography using existing digital methods. To this end, the authors introduce the ProMist-5K dataset, comprising 20,000 high-resolution image pairs generated through a physically inspired pipeline in scene-linear space, covering diverse combinations of filter densities and focal lengths. The proposed method employs a multi-layer blur framework with refined weighting strategies to precisely model both the intensity and spatial extent of light diffusion, enabling highly controllable yet photorealistic rendering. This dataset effectively supports various image translation models, successfully reproducing a spectrum of cinematic styles—from subtle to pronounced—under different training regimes, thereby significantly narrowing the gap between digital post-processing and traditional lens-based aesthetics.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Machine Learning: Multimodal Learning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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.

Problem

• Pro-Mist filter
• cinematic style emulation
• light diffusion
• digital image transformation
• optical effects

Innovation

• Pro-Mist filter
• cinematic style emulation
• optical diffusion
• physically inspired dataset
• highlight halation