BAT3R：从二维图像集合中自训练关节式三维重建
BAT3R: Bootstrapping Articulated 3D Reconstruction from 2D Image Collections
AI总结：
研究从单张图像进行关节物体3D重建，利用未标注2D图像集和单个绑定规范网格，提出训练框架，通过拟合网格到预测点图迭代估计关节和相机姿态，提升模型性能。
摘要：
从单张图像进行关节物体的3D重建具有挑战性，因为难以获得带配对图像和3D监督的大型训练数据集。近期基于点图的方法依赖人工创建的带精心策划姿态分布的关节3D资产渲染的合成数据集。我们提出一个训练框架，通过利用每个类别只有一个绑定规范网格的未标注2D图像集来减少这一需求。
英文摘要：
3D reconstruction of articulated objects from a single image is challenging because large training datasets with paired image and 3D supervision are difficult to obtain. Recent point map-based methods achieve strong performance but rely on synthetic datasets rendered from manually created articulated 3D assets with carefully curated pose distributions. While camera viewpoints can be easily sampled, generating realistic object articulations remains costly and labor-intensive. We propose a training framework that reduces this requirement by leveraging unannotated 2D images collections with only a single rigged canonical mesh per category. Starting from a weak 3D shape predictor trained on canonical-pose renders, we iteratively estimate object articulation and camera pose by fitting the mesh to predicted point maps. The recovered articulations and viewpoints are then used to render updated synthetic training data, progressively improving the predictor. Despite using substantially weaker 3D supervision, our models achieve performance comparable with DualPM, which requires manually curated articulated training datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
