Filters








3 Hits in 1.9 sec

AdaCoSeg: Adaptive Shape Co-Segmentation with Group Consistency Loss [article]

Chenyang Zhu, Kai Xu, Siddhartha Chaudhuri, Li Yi, Leonidas Guibas, Hao Zhang
2020 arXiv   pre-print
Then, the co-segmentation network iteratively and} jointly optimizes the part labelings across the set subjected to a novel group consistency loss defined by matrix ranks.  ...  While the part prior network can be trained with noisy and inconsistently segmented shapes, the final output of AdaCoSeg is a consistent part labeling for the input set, with each shape segmented into  ...  Our main contributions include: • The first DNN for adaptive shape co-segmentation. • A novel and effective group consistency loss based on low-rank approximations. • A co-segmentation training framework  ... 
arXiv:1903.10297v5 fatcat:kd625cwdqvdfvld6zzfcibucva

PartGlot: Learning Shape Part Segmentation from Language Reference Games [article]

Juil Koo, Ian Huang, Panos Achlioptas, Leonidas Guibas, Minhyuk Sung
2022 arXiv   pre-print
We introduce PartGlot, a neural framework and associated architectures for learning semantic part segmentation of 3D shape geometry, based solely on part referential language.  ...  Surprisingly, we further demonstrate that the learned part information is generalizable to shape classes unseen during training.  ...  Low Rank Regularization in AdaCoSeg [46] Table A8 . Results with the group consistency loss introduced by AdaCoSeg [46] . Bold indicates the best result for each column.  ... 
arXiv:2112.06390v2 fatcat:wvpdbuengjbhphnqfyvzotfvcu

RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures [article]

Chengjie Niu, Manyi Li, Kai Xu, Hao Zhang
2022
With reconstruction losses accounted for at each hierarchy level and a decomposition loss at each node, our network training does not require any ground-truth segmentations, let alone hierarchies.  ...  At each node of the tree, simultaneous feature decoding and shape decomposition are carried out by their respective feature and part decoders, with weight sharing across the same hierarchy level.  ...  AdaCoSeg [30] learns adaptive co-segmentation over a set of shapes using a group consistency loss.  ... 
doi:10.48550/arxiv.2201.12763 fatcat:vwfdbbhkubcsljjudejxttciqu