PulseAugur
实时 09:32:08
English(EN) PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Views

PASR框架通过姿态感知分析合成法改进三维形状检索

研究人员推出PASR,一个用于从单个、可能被遮挡的图像中进行三维形状检索的新型框架。PASR将DINOv3基础模型中的知识提炼到一个三维编码器中,实现了姿态条件三维投影和二维特征图之间的对齐。该方法将检索构建为一个分析合成问题,其中测试时优化搜索最佳形状和姿态以重建图像特征。该方法在处理遮挡方面比现有技术有了显著改进,并提供了包括姿态估计和类别分类在内的多任务能力。 AI

影响 增强了三维形状检索的鲁棒性,可能改进依赖于部分物体识别的AR/VR和机器人应用。

排序理由 介绍三维形状检索新方法的学术论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

PASR框架通过姿态感知分析合成法改进三维形状检索

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Jiaxin Shi, Guofeng Zhang, Wufei Ma, Naifu Liang, Adam Kortylewski, Alan Vuile ·

    PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Views

    arXiv:2604.22658v1 Announce Type: new Abstract: Single-view 3D shape retrieval is a fundamental yet challenging task that is increasingly important with the growth of available 3D data. Existing approaches largely fall into two categories: those using contrastive learning to map …

  2. arXiv cs.CV TIER_1 English(EN) · Alan Vuile ·

    PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Views

    Single-view 3D shape retrieval is a fundamental yet challenging task that is increasingly important with the growth of available 3D data. Existing approaches largely fall into two categories: those using contrastive learning to map point cloud features into existing vision-langua…