MirrorPPR: Exemplar-Based Portrait Photo Retouching

Hugging Face Daily Papers Papers
portrait-retouching exemplar-based diffusion-transformer lora data-augmentation image-editing

Summary

MirrorPPR introduces an exemplar-based portrait retouching framework using Diffusion Transformer with LoRA adaptation and self-augmented training data, achieving superior quality and identity preservation.

While text-guided image editing has made remarkable progress, it remains limited in structural portrait retouching. Textual descriptions struggle to convey fine-grained changes to facial features and body proportions. To address this gap, we introduce Exemplar-Based Portrait Photo Retouching, where the model is given an exemplar pair and tasked with inferring and applying the same retouching operations to a new query image. Existing exemplar-based editing methods primarily focus on tasks with pronounced visual transformations. In contrast, structural portrait retouching involves extremely delicate and localized modifications, making accurate extraction and transfer of these edits challenging. To tackle this, we propose MirrorPPR, a novel framework designed to capture and transfer subtle structural retouching operations. Our method uses a Retouching Operation Extractor to capture the subtle differences from the exemplar pair. The extracted representations are then injected into a pre-trained Diffusion Transformer (DiT) through a connector and Low-Rank Adaptation (LoRA) modules. Furthermore, constructing perfectly aligned cross-identity training pairs is severely hindered by operation misalignment. To overcome this, we propose an advanced data self-augmentation paradigm that ensures strictly aligned retouching operations. To alleviate data scarcity and support this novel task, we introduce MirrorPPR47M, a large-scale dataset with over 47 million retouched pairs. By structuring the dataset into simulated and professional subsets, we enable progressive curriculum learning to smoothly optimize the network. Extensive experiments demonstrate that MirrorPPR significantly outperforms existing baselines in both retouching quality and identity preservation. The project page is available at https://sjtu-deng-lab.github.io/MirrorPPR.
Original Article
View Cached Full Text

Cached at: 06/30/26, 11:38 PM

Paper page - MirrorPPR: Exemplar-Based Portrait Photo Retouching

Source: https://huggingface.co/papers/2606.29308

Abstract

Exemplar-based portrait retouching framework using Diffusion Transformer with LoRA adaptation and self-augmented training data achieves superior quality and identity preservation.

While text-guided image editing has made remarkable progress, it remains limited in structural portrait retouching. Textual descriptions struggle to convey fine-grained changes to facial features and body proportions. To address this gap, we introduce Exemplar-Based Portrait Photo Retouching, where the model is given an exemplar pair and tasked with inferring and applying the same retouching operations to a new query image. Existingexemplar-based editingmethods primarily focus on tasks with pronounced visual transformations. In contrast, structural portrait retouching involves extremely delicate and localized modifications, making accurate extraction and transfer of these edits challenging. To tackle this, we propose MirrorPPR, a novel framework designed to capture and transfer subtle structural retouching operations. Our method uses aRetouching Operation Extractorto capture the subtle differences from the exemplar pair. The extracted representations are then injected into a pre-trainedDiffusion Transformer(DiT) through a connector andLow-Rank Adaptation(LoRA) modules. Furthermore, constructing perfectly alignedcross-identity training pairsis severely hindered by operation misalignment. To overcome this, we propose an advanceddata self-augmentationparadigm that ensures strictly aligned retouching operations. To alleviate data scarcity and support this novel task, we introduce MirrorPPR47M, a large-scale dataset with over 47 million retouched pairs. By structuring the dataset into simulated and professional subsets, we enable progressivecurriculum learningto smoothly optimize the network. Extensive experiments demonstrate that MirrorPPR significantly outperforms existing baselines in both retouching quality and identity preservation. The project page is available at https://sjtu-deng-lab.github.io/MirrorPPR.

View arXiv pageView PDFProject pageGitHub3Add to collection

Get this paper in your agent:

hf papers read 2606\.29308

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.29308 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.29308 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.29308 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Mirror Learning

arXiv cs.LG

This paper proposes 'Mirror Learning', a framework for imitation learning from third-person observation that uses a fine-tuned video diffusion model for perspective transformation and an inverse dynamics model to synthesize pseudo first-person expert data, showing that this mirror data alone can train effective policies and improve behavior cloning.

MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation

Hugging Face Daily Papers

MirrorWorld is a reflection-aware video inpainting framework that improves mirror reflection generation in videos by separately modeling semantic content (SRD) and geometric spatial arrangements (GTA), achieving better reflection reconstruction than existing image-based and video inpainting baselines.