Hist2Style: Histogram-Guided Stylization with Bilateral Grids

2026-06-01

AI Summary

This work addresses the challenges of high computational cost, hallucination artifacts, and limited user control in high-resolution real-time photorealistic style transfer. To this end, the authors propose a lightweight, edge-aware stylization method based on bilateral grids. By distilling large image editing models into an efficient network and imposing local affine constraints in bilateral space, the approach effectively preserves content structure and fine details. Furthermore, it introduces a histogram-based, interpretable style embedding that enables intuitive user-controlled color adjustments. The resulting method supports real-time, high-resolution output, delivering high-quality, interactive photorealistic stylization while avoiding hallucinatory artifacts.

Abstract

Photorealistic style transfer aims to match the color and tone of an input image to that of a style target while preserving the content and details of the original scene. Although existing large image models can facilitate these kinds of appearance edits, their high computational demands, potential for hallucinations, and limited user control make them unsuitable for high-resolution, real-time workflows. We introduce Hist2Style, a bilateral-grid formulation for fast, edge-aware stylization that preserves visual fidelity by constraining operations to locally affine transforms in bilateral space. Our model distills a large image editing model into a lightweight network by training on a large supervised corpus generated with language and vision-language models, targeting spatially varying color edits. The network conditions on a histogram-based embedding of the style target to provide an interpretable interface for adjusting the output style by modifying the target color distribution. Overall, Hist2Style maintains content structure by construction, avoids hallucinations, and supports real-time, high-resolution photorealistic stylization with interactive user-controllable color and tone adjustments.

Problem

• photorealistic style transfer
• histogram-guided stylization
• real-time editing
• user control
• high-resolution stylization

Innovation

• bilateral grids
• photorealistic style transfer
• histogram-guided stylization
• local affine transforms
• model distillation