EOPose : Exemplar-based object reposing using Generalized Pose Correspondences

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mehrotra, Sarthak, Jain, Rishabh, Hemani, Mayur, Krishnamurthy, Balaji, Sarkar, Mausoom
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916722432278528
author Mehrotra, Sarthak
Jain, Rishabh
Hemani, Mayur
Krishnamurthy, Balaji
Sarkar, Mausoom
author_facet Mehrotra, Sarthak
Jain, Rishabh
Hemani, Mayur
Krishnamurthy, Balaji
Sarkar, Mausoom
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2505_03394
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EOPose : Exemplar-based object reposing using Generalized Pose Correspondences
Mehrotra, Sarthak
Jain, Rishabh
Hemani, Mayur
Krishnamurthy, Balaji
Sarkar, Mausoom
Computer Vision and Pattern Recognition
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
title EOPose : Exemplar-based object reposing using Generalized Pose Correspondences
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.03394