cs.CVNov 17, 2026

LUTBench: Benchmarking Text-Driven Photographic Look Transfer

Authors: Chuanzhi Xu, Boyu Wei, Chengkun Yue, Xuanhua Yin, Yiyang Li, Chupeng Liu, Zihan Deng, Weidong Cai

Organizations: The University of Sydney · Indiana University · The University of Hong Kong

Abstract

Photographic color grading shapes the tone and color of a photograph to achieve a desired look. Text-driven photographic look transfer lets users specify these adjustments in natural language, with the goal of reproducing the requested look across photographs while preserving their content. However, prior research on text-driven color grading uses different datasets, text instructions, target definitions, and metrics. These differences make it difficult to compare how faithfully the methods reproduce the same look. To compare methods under a shared protocol, we introduce LUTBench. We collect 91 three-dimensional lookup tables (3D LUTs) and define one photographic look per LUT with a specified input conversion. Applying these looks to 5,000 MIT-Adobe FiveK photographs produces 455,000 input-target image pairs with reproducible target images. For each look, we use templates to turn measured tone and color changes on fixed color samples into candidate clauses. We use training image measurements to verify applicable clauses before composing the text description. The evaluation measures target fidelity, tests sensitivity to predefined input conversions, and separates generalization to unseen looks from reproduction of seen looks on new photographs. Across 16 methods, stronger text alignment does not guarantee target fidelity. However, most supervised variants improve fidelity on both seen and unseen looks.

Figures & tables

Appendix figures & tables18 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. AceTone: Bridging Words and Colors for Conditional Image Grading

    Apr 1, 2026Tianren Ma, Mingxiang Liao, Xijin Zhang +1Image EditingText-Guided Image Editing

  2. UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation

    Oct 7, 2026Deyuan Liu, Yihao Hu, Jingxuan Zhang +13Text Rendering in T2I GenerationT2I Generation Evaluation

  3. DefaultShift: Auditing Semantic Default Shift in Accelerated Text-to-Image Models

    Aug 22, 2026Xuanhua Yin, Chuanzhi Xu, Shunqi Mao +2T2I Generation EvaluationT2I Diffusion Models