MirrorPPR：基於範例的人像照片修圖

摘要

雖然文字引導的影像編輯已取得顯著進展，但在結構性肖像修圖方面仍有限制。文字描述難以傳達對臉部特徵與身體比例的細微變化。為解決此一差距，我們引入了基於範例的肖像照片修圖，其中模型被給予一組範例對，並需推斷相同的修圖操作，將其應用於新的查詢影像。現有的基於範例的編輯方法主要聚焦於具有明顯視覺轉變的任務。相比之下，結構性肖像修圖涉及極其細膩且局部化的修改，使得準確提取與轉移這些編輯極具挑戰。為解決此問題，我們提出了MirrorPPR，一個旨在捕捉並傳遞細微結構性修圖操作的新穎框架。我們的方法使用修圖操作提取器，從範例對中捕捉細微差異；接著，透過連接器與低秩適應（LoRA）模組，將提取的表徵注入預訓練的擴散Transformer（DiT）中。此外，構建完美對齊的跨身份訓練對，由於操作不對齊而受到嚴重阻礙。為克服此問題，我們提出了一個先進的資料自我增強範例，確保嚴格的對齊修圖操作。為緩解資料稀缺並支援此新穎任務，我們引入了MirrorPPR47M——一個包含超過4700萬組修圖對的大規模資料集。透過將資料集結構化為模擬與專業子集，我們實現了漸進式課程學習，以平穩優化網路。廣泛的實驗表明，MirrorPPR在修圖品質與身份保留方面均顯著優於現有基準。專案頁面可在 https://sjtu-deng-lab.github.io/MirrorPPR 取得。

English

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.