EOPose : Exemplar-based object reposing using Generalized Pose Correspondences
This work addresses the need for efficient product image generation in e-commerce, but it is incremental as it builds on existing keypoint correspondence techniques.
The paper tackles the problem of reposing objects in images for applications like e-commerce by proposing EOPose, an end-to-end framework that uses unsupervised keypoint correspondences to warp and re-render source objects into target poses while preserving fine details. The method achieves high-quality results, as shown by metrics such as PSNR, SSIM, and FID, and is validated with ablation and user studies.
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