Structure-Preserving 3D Garment Modeling with Neural Sewing Machines
Nov 28, 2022
Speakers
Xipeng Chen
Speaker · 0 followers
Guangrun Wang
Speaker · 0 followers
Dizhong Zhu
Speaker · 0 followers
Xiaodan Liang
Speaker · 0 followers
Philip H. S. Torr
Speaker · 0 followers
About
3D Garment modeling is a critical and challenging topic in the area of computer vision and graphics, with increasing attention focused on garment representation learning, garment reconstruction, and controllable garment manipulation. Whereas existing methods were constrained to model garments under specific categories or with simple topology, and failed to learn reconstructable and manipulable representations. In this paper, we propose a novel Neural Sewing Machine (NSM), a learning-based framework for structure-preserving 3D garment modeling, which is capable of modeling and learning representations for garments with diverse shapes and topologies and is successfully applied to 3D garment reconstruction and controllable manipulation. To model generic garments, we first obtain sewing pattern embedding via a unified sewing pattern encoding module as the sewing pattern can accurately describe the intrinsic structure and the topology of the 3D garment. Then we use a 3D garment decoder to decode the sewing pattern embedding into a 3D garment using the UV-position maps with masks. To preserve the intrinsic structure of the predicted 3D garment, we introduce an inner-panel structure-preserving loss, an inter-panel structure-preserving loss, and a surface-normal loss in the learning process of our framework. We evaluate NSM on the public 3D garment dataset with sewing patterns with diverse garment shapes and categories. Extensive experiments demonstrate that the proposed NSM is capable of representing 3D garments under diverse garment shapes and topologies, realistically reconstructing 3D garments from 2D images with the preserved structure, and accurately manipulating the 3D garment categories, shapes, and topologies, outperforming the state-of-the-art methods by a clear margin.3D Garment modeling is a critical and challenging topic in the area of computer vision and graphics, with increasing attention focused on garment representation learning, garment reconstruction, and controllable garment manipulation. Whereas existing methods were constrained to model garments under specific categories or with simple topology, and failed to learn reconstructable and manipulable representations. In this paper, we propose a novel Neural Sewing Machine (NSM), a learning-based framew…
Organizer
NeurIPS 2022
Account · 952 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
A Stochastic Prox-Linear Method for CVaR Minimization
Watch later
Si Yi Meng, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Understanding Square Loss in Training Overparametrized Neural Network Classifiers
Watch later
Tianyang Hu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Scalable Distributional Robustness in a Class of Non-Convex Optimization with Guarantees
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Let Images Give You More: Point Cloud Cross-Modal Training for Shape Analysis
Watch later
Xu Yan, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Local Identifiability of Deep ReLU Neural Networks: the Theory
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%