# FashionPose: Unified Text-Driven Fashion Synthesis with Joint Geometric and Photometric Control

arXiv: https://arxiv.org/abs/2507.13311 · HTML: https://mlsanity.com/paper/2507.13311/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 17 Jul 2025.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [Pose Guided Person Image Generation](https://mlsanity.com/paper/1705.09368/) (2017)
- [Person Image Synthesis via Denoising Diffusion Model](https://mlsanity.com/paper/2211.12500/) (2022)
- [Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models](https://mlsanity.com/paper/2310.06313/) (2023)
- [Exploring Dual-task Correlation for Pose Guided Person Image Generation](https://mlsanity.com/paper/2203.02910/) (2022)
- [Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model](https://mlsanity.com/paper/2502.09533/) (2025)
- [Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis](https://mlsanity.com/paper/2402.18078/) (2024)
- [SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction](https://mlsanity.com/paper/2503.18211/) (2025)
- [SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces](https://mlsanity.com/paper/2501.09756/) (2025)
- [Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization](https://mlsanity.com/paper/2504.03011/) (2025)
- [MoRAG -- Multi-Fusion Retrieval Augmented Generation for Human Motion](https://mlsanity.com/paper/2409.12140/) (2024)
- [Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions](https://mlsanity.com/paper/2504.03639/) (2025)
- [MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training](https://mlsanity.com/paper/2406.01867/) (2024)
- [Adversarial Synthesis of Human Pose from Text](https://mlsanity.com/paper/2005.00340/) (2020)
- [Controlling Human Shape and Pose in Text-to-Image Diffusion Models via Domain Adaptation](https://mlsanity.com/paper/2411.04724/) (2024)
- [FineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injection](https://mlsanity.com/paper/2312.09252/) (2023)
- [GUNet: A Graph Convolutional Network United Diffusion Model for Stable and Diversity Pose Generation](https://mlsanity.com/paper/2409.11689/) (2024)

## Abstract (arXiv)

Realistic and controllable garment synthesis is essential for fashion e-commerce, yet it demands precise coordination between human pose geometry and environmental photometry. Conventional pose-guided frameworks suffer from two fundamental limitations: they rely heavily on predefined skeletons from off-the-shelf estimators, restricting semantic flexibility; and they predominantly focus on studio-like generation under neutral lighting, failing to reconcile geometric configurations with complex, scene-specific illumination described in natural language. To bridge this gap, we propose FashionPose, a cascaded architecture that reconciles geometric and photometric control within a unified language-driven interface. Unlike conventional frameworks, our framework employs a decoupled yet synergistic strategy: (1) a bidirectional contrastive alignment mechanism that grounds textual semantics into an explicit geometric manifold, enabling template-free pose generation; (2) an identity-anchored synthesis module that translates these geometric priors into high-fidelity imagery while preserving fine-grained appearance; and (3) a prompt-conditioned relighting module that leverages the generated pose as a spatial anchor to achieve environment-aware shading. This hierarchical design effectively transforms high-level instructions into consistent visual representations, ensuring both structural precision and atmospheric harmony. To facilitate this paradigm, we construct PoseCap, a dataset with over 40,000 caption-keypoint pairs. Extensive experiments demonstrate that FashionPose outperforms existing benchmarks in pose accuracy and physical realism, providing a robust solution for personalized, scene-aware virtual fashion displays.