EOPose : Exemplar-based object reposing using Generalized Pose Correspondences

TL;DR

EOPose is an end-to-end framework that reposes objects in images by leveraging unsupervised keypoint correspondence detection, enabling high-quality, detail-preserving reposing suitable for applications like e-commerce.

Contribution

The paper introduces EOPose, a novel method that uses keypoint correspondences for object reposing, preserving details and avoiding generative artifacts, along with a new paired object dataset.

Findings

EOPose achieves high scores on PSNR, SSIM, and FID metrics.

The method outperforms existing approaches in detail preservation.

User studies confirm the effectiveness of the reposing quality.

Abstract

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