用关键点对应关系实现物体图像的精准姿态重置
EOPose : Exemplar-based object reposing using Generalized Pose Correspondences
- 基于同类物体间无监督关键点匹配，构建端到端重姿框架
- 在PSNR、SSIM和FID指标上优于现有方法，保留纹理与品牌标识
- 适合电商快速生成多姿态商品图，支持细粒度视觉保持
图像中物体重姿具有广泛的应用，尤其在电商领域需快速生成产品多视角图像。本文利用同一类别物体间无监督关键点对应检测的最新进展，提出一种端到端的通用物体重姿框架EOPose。该方法以目标姿态引导图像为输入，通过其与源图像的关键点对应关系，采用三步新策略对源图像进行形变与重渲染，生成目标姿态图像。与生成式方法不同，本方法能有效保留物体的精细细节，如精确颜色、纹理及品牌标记。同时，我们基于Objaverse数据集构建了一个新的配对物体数据集，用于模型训练与测试。实验结果表明，EOPose在多个图像质量指标（PSNR、SSIM、FID）上表现优异。论文还包含详细的消融实验与用户研究，验证了方法的有效性。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。