---
title: "PREEN: Exemplar-Based Color Style Transfer with Smartphone Editor Presets"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.36896v1"
permalink: "https://feed.astralor.com/items/itm_ff270dd0e15d950afcaa3eda"
published: "2026-10-27T09:30:35.000Z"
score: 56
channel: "tech"
tags: ["推理效率","多模态","PREEN","Exemplar-Based Color Style","Transfer","Smartphone Editor Presets","Preset Regression","Exemplar-based Editor Network"]
---

# PREEN: Exemplar-Based Color Style Transfer with Smartphone Editor Presets

## 速览

We present PREEN (Preset Regression via an Exemplar-based Editor Network), which casts color style transfer as regression onto the 29 parameters of a deterministic image editor. Given a content image and a style referen…

## 关键点

- We present PREEN (Preset Regression via an Exemplar-based Editor Network), which casts color style transfer as regression onto the 29 parameters of a deterministic image editor.
- Given a content image and a style reference, PREEN predicts a preset, a vector of editor slider values that is interpretable and editor-consumable, not a raster image.
- The key obstacle is supervision, since an arbitrary real reference lacks a preset ground truth.

## 全文

We present PREEN (Preset Regression via an Exemplar-based Editor Network), which casts color style transfer as regression onto the 29 parameters of a deterministic image editor. Given a content image and a style reference, PREEN predicts a preset, a vector of editor slider values that is interpretable and editor-consumable, not a raster image. The key obstacle is supervision, since an arbitrary real reference lacks a preset ground truth. We therefore supervise with a style-transfer teacher, whose target looks we invert into the editor's parameter space as pseudo-presets, then pretrain a CLIP-conditioned regressor and refine it with LoRA under an image-level CIELAB loss. On the human-curated PST50 benchmark, PREEN applies the reference's color while preserving structural fidelity, leading the baselines on pixel- and perceptual-fidelity metrics. The preset is compact and predicted at sub-second on-device latency. The low-dimensional subspace also exposes a single inference-time strength knob that traces a continuous default-to-vivid trajectory in one forward pass, with every intermediate state a valid editor preset. A two-axis human study shows that raters prefer the vivid end for matching the reference but the default as a standalone photo, a trade-off the knob spans without retraining.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_ff270dd0e15d950afcaa3eda