ATune: Unsupervised Photo Retouching Through Image-Editor Controls

Divyanshu Goyal, Gabriel Ruiz, Amir MeisamiarXiv 2026 · arXiv

TL;DR

ATune is a self-supervised photo retouching model that learns to enhance images by reversing synthetic degradations on a massive corpus of 10 million stock photographs. Instead of directly manipulating pixels, it predicts "declarative" targets for 13 human-interpretable attributes (like sharpness and contrast) to drive off-the-shelf editors like RawTherapee, matching the performance of frontier models like Claude Opus 5 without requiring a single expert-retouched training pair.

What Problem Does This Paper Address?

Traditional photo retouching models rely on supervised learning from pairs of "before" and "after" images edited by experts. However, expert edits are prohibitively expensive and time-consuming to produce. As a result, standard datasets like MIT-Adobe FiveK are relatively small (~5,000 images), leading to models that struggle to generalize to diverse, real-world photographs.

Furthermore, many existing AI retouchers are "black boxes" that output final pixels or use internal, non-standard operations. This makes it impossible for a human photographer to understand, undo, or fine-tune the AI's decisions using familiar tools like sliders in a standard image editor.

Methods

ATune introduces a three-step Measure-Predict-Act pipeline that shifts retouching from pixel manipulation to declarative goal-setting:

  1. Measure: The system defines a space of 13 measurable image attributes (e.g., brightness, color temperature, haze, noise). These measures were specifically selected for their stability under common operations like resizing or JPEG compression.
  2. Predict: The core model—a 54M-parameter residual MLP conditioned on DINOv3 embeddings—is trained using a "Distort-and-Recover" strategy. The authors take high-quality stock photos, synthetically "damage" them (e.g., adding blur, noise, or exposure errors), and task the model with predicting the attribute changes needed to return to the original quality. Crucially, the model is conditioned on a "quality dial" ($\tau$), allowing users to specify how much of an enhancement they want.
  3. Act: ATune doesn't set sliders directly. Instead, it sets target values for the 13 attributes. A numerical solver (Levenberg-Marquardt) then iteratively adjusts the sliders of an external, out-of-the-box editor (like RawTherapee or darktable) until the image's measured attributes match the model's predicted targets.
Figure 1. Retouching learned from unpaired photographs. On a FiveK test photograph, ATune predicts how far each attribute should move to reach a desired quality set by τ; a simple search sets RawTherapee’s or darktable’s sliders until the measured attributes land there. Insets: the boxed region at 100%; scores: Q-Align quality and aesthetics.

Datasets

  • Training: A massive, licensed commercial stock collection of 10 million photographs. The model uses only the "good" finished versions for self-supervision via synthetic degradation.
  • Evaluation:
    • MIT-Adobe FiveK: The standard benchmark for global tonal adjustment.
  • PPR10K: A large-scale portrait photo retouching dataset.
  • SPAQ: A dataset of smartphone photographs used to test generalization to non-professional hardware.

Key Insights and Ideas

  • Declarative vs. Imperative Editing: Most models provide an imperative edit (a sequence of operations). ATune provides a declarative edit (a target state). This makes the model editor-agnostic; the same model can drive different software just by calibrating how that software's sliders affect the 13 core attributes.
  • Scaling with Data, Not Labels: The authors found that performance consistently improves as the training set grows from 1M to 10M images. This suggests that the bottleneck for photo retouching isn't the lack of expert labels, but rather the diversity and volume of the "target" distribution of good photos.
  • Human-in-the-Loop Transparency: Because the output is a set of standard editor sliders, the AI's "reasoning" is fully transparent and editable. A photographer can see that the AI decided to increase sharpness by +28 and manually dial it back if they disagree.
Scaling results showing that more training photographs lead to better edits across all test sets.

Key Results

  • Human Preference: In a large-scale user study, human raters preferred ATune's edits to those of GPT-6 Astra (54.3%) and rated them as equal to Claude Opus 5 (50.5%).
  • Supervised Parity: Despite having no expert supervision, ATune achieved near-parity (46.3% preference) with state-of-the-art supervised models (NeurOP and AdaInt) even when those models were tested on the specific datasets they were trained on.
  • Generalization: ATune significantly outperformed supervised models on the SPAQ (smartphone) dataset, demonstrating that training on 10M diverse stock photos yields much better generalization than training on small expert sets.

Limitations and Future Work

  • Global Edits Only: Currently, ATune treats the entire image as one unit. It cannot perform local edits, such as retouching only a face or changing the sky independently.
  • Inference Speed: The iterative numerical search is slow, taking a median of 42 seconds per photograph. While this is acceptable for batch processing, it is too slow for interactive use.
  • Future Directions: The authors suggest training a secondary "distillation" network that maps predicted attribute targets directly to slider values, which could reduce the "Act" step from seconds to milliseconds.

Summary updated

Abstract

Photo retouching models are trained on pairs of original and retouched photographs, usually edited by experts. Expert edits are costly, so the two main public sets, FiveK and PPR10K, hold only 16,161 originals. Good photographs on their own are far easier to find: commercial stock collections and free ones such as Pixabay and Unsplash hold millions. We learn retouching from them alone: we damage each photograph the way a camera or a careless edit would, which gives a worse and a better version of the same photograph. From these pairs, our model, ATune, learns how 13 measured attributes, such as brightness, contrast and sharpness, should change to raise a photograph's quality. The edit is declarative: ATune sets target values for the attributes, and a simple search adjusts the sliders of an out-of-the-box photo editor until the photograph reaches them. Every edit is a list of slider values a person can read and adjust. The same model can drive any editor that makes those changes; we test RawTherapee and darktable. We train on 10M photographs from a commercial stock collection and test on FiveK, PPR10K and SPAQ. Nine quality judges score every edit, and in a user study 157 human raters made 9,253 choices between our edit and another method's edit of the same photograph. When Claude Opus 5 and GPT-6 Astra edit the same photographs in the same editor, raters prefer our edits to GPT-6 Astra's (54.3%) and rate them even with Claude's (50.5%). We also compare with supervised retouchers on their home ground: NeurOP on FiveK and AdaInt on PPR10K, each trained on that set's own expert edits. Raters chose our edits in 46.3% of those comparisons. ATune, a 54M-parameter model trained without a single expert edit, now matches frontier models at setting an editor's sliders.
BibTeX
@misc{goyal2026atune,
  author = {Divyanshu Goyal and Gabriel Ruiz and Amir Meisami},
  title = {{ATune: Unsupervised Photo Retouching Through Image-Editor Controls}},
  year = {2026},
  eprint = {2611.16236},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.16236},
}
Figure