AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

AceTone: Bridging Words and Colors for Conditional Image Grading

Tianren Ma, Mingxiang Liao, Xijin Zhang, Qixiang Ye

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add aesthetic reward to color similarity reward (ablation)AceTone GRPO · AceTone-Bench TransferAes.: 3.29 -> 3.57Improved
add aesthetic reward to color similarity reward (ablation)AceTone GRPO · AceTone-Bench TransferDeltaE: 8.93 -> 8.98No clear effect
add LPIPS reward to color reward (ablation)AceTone GRPO · AceTone-Bench TransferLPIPS: 0.11 -> 0.10No clear effect
add PSNR reward to color reward (ablation)AceTone GRPO · AceTone-Bench TransferPSNR: 22.51 -> 22.58No clear effect
add GRPO reinforcement learning after SFT (ablation)AceTone · AceTone-Bench Transfercolor metricsImproved
use a harder RL LUT pool (8K LUTs) for data curation (ablation)AceTone GRPO · AceTone-Bench TransfergeneralizationImproved
generate LUTs with AceTone instead of diffusion editingInstructPix2Pix and Qwen-Image-Edit · AceTone-Bench InstructLPIPS: 0.33 -> 0.22Improved
use AceTone instead of JarvisArtJarvisArt · AceTone-Bench InstructGemini rank: 2.72 -> 1.43Improved
use AceTone instead of SA-LUTSA-LUT · AceTone-Bench TransferDeltaE: 13.10 -> 8.98Improved
use AceTone instead of SA-LUTSA-LUT · PST-50LPIPS: 0.16 -> 0.09Improved
use discrete VQ tokenizer instead of continuous LUT compressionLUT compression · LUT reconstructionDeltaE: 3.11 -> 1.38Improved
use AceTone instead of Qwen-Image-Edit in user study (IGG)Qwen-Image-Edit · user study IGGPref. (%): 34.8 -> 46.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy