Hist2Style: Histogram-Guided Stylization with Bilateral Grids

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 realtime, high-resolution photorealistic stylization with interactive user-controllable color and tone adjustments. Our project page is available at dgalor.github.io/hist2style/.

Recently, large image editing models have transformed how users approach stylization [21,47,52]. These models let users specify visual intentions through image or text prompts, promising far greater flexibility than traditional style transfer methods [21]. In principle, their expressive power could render specialized photorealistic stylization algorithms obsolete, but in practice this versatility introduces key limitations.