# EOPose : Exemplar-based object reposing using Generalized Pose Correspondences

arXiv: https://arxiv.org/abs/2505.03394 · HTML: https://mlsanity.com/paper/2505.03394/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 45 references that are in the map.
- First posted on arXiv 6 May 2025.

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [VITON: An Image-based Virtual Try-on Network](https://mlsanity.com/paper/1711.08447/) (2017)
- [A Note on the Inception Score](https://mlsanity.com/paper/1801.01973/) (2018)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [Toward Characteristic-Preserving Image-based Virtual Try-On Network](https://mlsanity.com/paper/1807.07688/) (2018)
- [DeepHuman: 3D Human Reconstruction from a Single Image](https://mlsanity.com/paper/1903.06473/) (2019)
- [BodyNet: Volumetric Inference of 3D Human Body Shapes](https://mlsanity.com/paper/1804.04875/) (2018)
- [Dense Intrinsic Appearance Flow for Human Pose Transfer](https://mlsanity.com/paper/1903.11326/) (2019)
- [IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation](https://mlsanity.com/paper/2403.10701/) (2024)
- [ControlCom: Controllable Image Composition using Diffusion Model](https://mlsanity.com/paper/2308.10040/) (2023)
- [StarMap for Category-Agnostic Keypoint and Viewpoint Estimation](https://mlsanity.com/paper/1803.09331/) (2018)
- [ZFlow: Gated Appearance Flow-based Virtual Try-on with 3D Priors](https://mlsanity.com/paper/2109.07001/) (2021)
- [3D Human Body Reconstruction from a Single Image via Volumetric Regression](https://mlsanity.com/paper/1809.03770/) (2018)
- [M&M VTO: Multi-Garment Virtual Try-On and Editing](https://mlsanity.com/paper/2406.04542/) (2024)
- [MV-VTON: Multi-View Virtual Try-On with Diffusion Models](https://mlsanity.com/paper/2404.17364/) (2024)
- [SieveNet: A Unified Framework for Robust Image-Based Virtual Try-On](https://mlsanity.com/paper/2001.06265/) (2020)
- [PoNA: Pose-guided Non-local Attention for Human Pose Transfer](https://mlsanity.com/paper/2012.07049/) (2020)
- [Learning Continuous 3D Words for Text-to-Image Generation](https://mlsanity.com/paper/2402.08654/) (2024)
- [Lightplane: Highly-Scalable Components for Neural 3D Fields](https://mlsanity.com/paper/2404.19760/) (2024)
- [Best-Buddies Similarity - Robust Template Matching using Mutual Nearest Neighbors](https://mlsanity.com/paper/1609.01571/) (2016)

## Abstract (arXiv)

Reposing objects in images has a myriad of applications, especially for e-commerce where several variants of product images need to be produced quickly. In this work, we leverage the recent advances in unsupervised keypoint correspondence detection between different object images of the same class to propose an end-to-end framework for generic object reposing. Our method, EOPose, takes a target pose-guidance image as input and uses its keypoint correspondence with the source object image to warp and re-render the latter into the target pose using a novel three-step approach. Unlike generative approaches, our method also preserves the fine-grained details of the object such as its exact colors, textures, and brand marks. We also prepare a new dataset of paired objects based on the Objaverse dataset to train and test our network. EOPose produces high-quality reposing output as evidenced by different image quality metrics (PSNR, SSIM and FID). Besides a description of the method and the dataset, the paper also includes detailed ablation and user studies to indicate the efficacy of the proposed method