# Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer

arXiv: https://arxiv.org/abs/2606.31089 · HTML: https://mlsanity.com/paper/2606.31089/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 55 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Builds on (most cited first, 10 of 10)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Prodigy: An Expeditiously Adaptive Parameter-Free Learner](https://mlsanity.com/paper/2306.06101/) (2023)
- [OminiControl2: Efficient Conditioning for Diffusion Transformers](https://mlsanity.com/paper/2503.08280/) (2025)
- [CycleDiff: Cycle Diffusion Models for Unpaired Image-to-image Translation](https://mlsanity.com/paper/2508.06625/) (2025)
- [Semi-parametric Makeup Transfer via Semantic-aware Correspondence](https://mlsanity.com/paper/2203.02286/) (2022)
- [EvoMakeup: High-Fidelity and Controllable Makeup Editing with MakeupQuad](https://mlsanity.com/paper/2508.05994/) (2025)

## Abstract (arXiv)

Makeup transfer applies a reference cosmetic style to a source face while preserving its identity and geometry. However, this task is severely hindered by the lack of real paired training data. Current methods rely on either weak priors or synthetic pseudo-targets from large-scale editing models. These paradigms provide suboptimal guidance, often leading to degraded fine-grained details, synthetic artifacts, and identity drift. To this end, we propose Anchoring on Reality Makeup Transfer (ART), a two-stage framework with a reality-anchored refinement cycle. In Stage I, the model is initialized with pseudo-targets to establish basic semantic alignment and global makeup placement. Crucially, Stage II shifts supervision from pseudo-targets to the real reference, reconstructing it from its bare-skin counterpart through a differentiable cycle that penalizes any omitted detail and overrides synthetic artifacts. Furthermore, we introduce MakeupFaces2K (MF2K), the first 2K-resolution in-the-wild makeup portrait dataset comprising 8,573 images. Extensive experiments demonstrate that our method achieves superior makeup fidelity, strong background stability, and robust identity preservation, especially for complex makeup styles.