arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.04755cs.CV
收藏

三维形状编辑中语义参数的学习推理

Learning to Infer Semantic Parameters for 3D Shape Editing

Princeton University(普林斯顿大学);New York University(纽约大学);Google Research(谷歌研究院)

Fangyin Wei, Elena Sizikova, Avneesh Sud, Szymon Rusinkiewicz, Thomas Funkhouser

摘要:

3D形状设计和增强中的许多应用需要对对象的语义参数(例如,一个人的手臂的姿势或飞机机翼的长度),同时尽可能多地保留现有的细节。我们建议学习一个深度网络,该网络推断输入形状的语义参数,然后允许用户操纵这些参数。该网络在来自辅助合成模板和未标记的真实模型的形状上进行联合训练,确保了对形状变化的鲁棒性,同时减轻了对标记真实样本的需求。在测试时,参数空间内的编辑驱动变形应用于原始形状,这提供了语义上有意义的操作,同时保留了细节。这与先前的方法形成对比,先前的方法要么使用具有有限潜在空间维度的自动编码器,无法保留任意细节,要么使用纯几何控制(如笼子)驱动变形,失去更新局部零件区域的能力。椅子,飞机和人体数据集的实验表明,我们的方法比以前的工作产生更自然的编辑。

英文摘要:

Many applications in 3D shape design and augmentation require the ability to make specific edits to an object's semantic parameters (e.g., the pose of a person's arm or the length of an airplane's wing) while preserving as much existing details as possible. We propose to learn a deep network that infers the semantic parameters of an input shape and then allows the user to manipulate those parameters. The network is trained jointly on shapes from an auxiliary synthetic template and unlabeled realistic models, ensuring robustness to shape variability while relieving the need to label realistic exemplars. At testing time, edits within the parameter space drive deformations to be applied to the original shape, which provides semantically-meaningful manipulation while preserving the details. This is in contrast to prior methods that either use autoencoders with a limited latent-space dimensionality, failing to preserve arbitrary detail, or drive deformations with purely-geometric controls, such as cages, losing the ability to update local part regions. Experiments with datasets of chairs, airplanes, and human bodies demonstrate that our method produces more natural edits than prior work.

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。

↑