# Towards Fine-grained Human Pose Transfer with Detail Replenishing Network

arXiv: https://arxiv.org/abs/2005.12494 · HTML: https://mlsanity.com/paper/2005.12494/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2020.

## Built on by (most cited first, 21 of 21)

- [HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation](https://mlsanity.com/paper/2304.04269/) (2023)
- [HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion](https://mlsanity.com/paper/2310.08579/) (2023)
- [Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects](https://mlsanity.com/paper/2112.11347/) (2021)
- [Cross Attention Based Style Distribution for Controllable Person Image Synthesis](https://mlsanity.com/paper/2208.00712/) (2022)
- [Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation](https://mlsanity.com/paper/2311.15841/) (2023)
- [HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challenge](https://mlsanity.com/paper/2110.00119/) (2021)
- [Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation](https://mlsanity.com/paper/2403.05239/) (2024)
- [Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesis](https://mlsanity.com/paper/2109.02081/) (2021)
- [Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistency](https://mlsanity.com/paper/2110.05458/) (2021)
- [GRPose: Learning Graph Relations for Human Image Generation with Pose Priors](https://mlsanity.com/paper/2408.16540/) (2024)
- [KPE: Keypoint Pose Encoding for Transformer-based Image Generation](https://mlsanity.com/paper/2203.04907/) (2022)
- [RANA: Relightable Articulated Neural Avatars](https://mlsanity.com/paper/2212.03237/) (2022)
- [UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer](https://mlsanity.com/paper/2304.08870/) (2023)
- [Human Image Generation: A Comprehensive Survey](https://mlsanity.com/paper/2212.08896/) (2022)
- [BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion](https://mlsanity.com/paper/2404.04544/) (2024)
- [DiffBody: Human Body Restoration by Imagining with Generative Diffusion Prior](https://mlsanity.com/paper/2404.03642/) (2024)
- [FDA-GAN: Flow-based Dual Attention GAN for Human Pose Transfer](https://mlsanity.com/paper/2112.00281/) (2021)
- [A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer](https://mlsanity.com/paper/2109.11719/) (2021)
- [DRaCoN -- Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars](https://mlsanity.com/paper/2203.15798/) (2022)
- [KB-DMGen: Knowledge-Based Global Guidance and Dynamic Pose Masking for Human Image Generation](https://mlsanity.com/paper/2507.20083/) (2025)
- [One-Shot Novel View and Pose Human Image Synthesis via 3D Prior Guided Diffusion Model](https://mlsanity.com/paper/2606.19718/) (2026)

## Abstract (arXiv)

Human pose transfer (HPT) is an emerging research topic with huge potential in fashion design, media production, online advertising and virtual reality. For these applications, the visual realism of fine-grained appearance details is crucial for production quality and user engagement. However, existing HPT methods often suffer from three fundamental issues: detail deficiency, content ambiguity and style inconsistency, which severely degrade the visual quality and realism of generated images. Aiming towards real-world applications, we develop a more challenging yet practical HPT setting, termed as Fine-grained Human Pose Transfer (FHPT), with a higher focus on semantic fidelity and detail replenishment. Concretely, we analyze the potential design flaws of existing methods via an illustrative example, and establish the core FHPT methodology by combing the idea of content synthesis and feature transfer together in a mutually-guided fashion. Thereafter, we substantiate the proposed methodology with a Detail Replenishing Network (DRN) and a corresponding coarse-to-fine model training scheme. Moreover, we build up a complete suite of fine-grained evaluation protocols to address the challenges of FHPT in a comprehensive manner, including semantic analysis, structural detection and perceptual quality assessment. Extensive experiments on the DeepFashion benchmark dataset have verified the power of proposed benchmark against start-of-the-art works, with 12%-14% gain on top-10 retrieval recall, 5% higher joint localization accuracy, and near 40% gain on face identity preservation. Moreover, the evaluation results offer further insights to the subject matter, which could inspire many promising future works along this direction.