paper-with-me

홈 › Papers

KTNet: Knowledge Transfer for Unpaired 3D Shape Completion

2021-11-23 · Zhen Cao, Wenxiao Zhang, Xin Wen, Zhen Dong, Yu-Shen Liu, Xiongwu Xiao, Bisheng Yang

Unpaired 3D object completion aims to predict a complete 3D shape from an incomplete input without knowing the correspondence between the complete and incomplete shapes. In this paper, we propose the novel KTNet to solve this task from the new perspective of knowledge transfer. KTNet elaborates a teacher-assistant-student network to establish multiple knowledge transfer processes. Specifically, the teacher network takes complete shape as input and learns the knowledge of complete shape. The student network takes the incomplete one as input and restores the corresponding complete shape. And the assistant modules not only help to transfer the knowledge of complete shape from the teacher to the student, but also judge the learning effect of the student network. As a result, KTNet makes use of a more comprehensive understanding to establish the geometric correspondence between complete and incomplete shapes in a perspective of knowledge transfer, which enables more detailed geometric inference for generating high-quality complete shapes. We conduct comprehensive experiments on several datasets, and the results show that our method outperforms previous methods of unpaired point cloud completion by a large margin.

📄 PDF Abstract BibTeX arXiv:2111.11976

Code (2)

2023-MindSpore-1/ms-code-5/tree/main/ktnet mindspore
MindSpore-paper-code-3/code9/tree/main/ktnet mindspore

Tasks

Point Cloud CompletionTransfer Learning

Similar Papers 제목 키워드 기반

Knowledge Mining and Transferring for Domain Adaptive Object Detection

2021-01-01 · ICCV 2021 10 · Kun Tian, Chenghao Zhang, Ying Wang, Shiming Xiang 외

With the thriving of deep learning, CNN-based object detectors have made great progress in the past decade. However, the domain gap between training and testing data leads to a prominent performance degradation and t…

AttributeDomain AdaptationObjectobject-detection+2

From Limited Labels to Open Domains: An Efficient Learning Paradigm for UAV-view Geo-Localization

2025-03-10 · Zhongwei Chen, Zhao-Xu Yang, Hai-Jun Rong, Jiawei Lang

Traditional UAV-view Geo-Localization (UVGL) supervised paradigms are constrained by the strict reliance on paired data for positive sample selection, which limits their ability to learn cross-view domain-invariant repre…

geo-localizationTransfer Learning

Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding

2021-03-14 · CVPR 2021 1 · Xin Wen, Zhizhong Han, Yan-Pei Cao, Pengfei Wan 외

In this paper, we present a novel unpaired point cloud completion network, named Cycle4Completion, to infer the complete geometries from a partial 3D object. Previous unpaired completion methods merely focus on the learn…

Point Cloud Completion

RefComp: A Reference-guided Unified Framework for Unpaired Point Cloud Completion

2025-04-18 · Yixuan Yang, Jinyu Yang, Zixiang Zhao, Victor Sanchez 외

The unpaired point cloud completion task aims to complete a partial point cloud by using models trained with no ground truth. Existing unpaired point cloud completion methods are class-aware, i.e., a separate model is ne…

Point Cloud CompletionTranslation

Data-Efficient Goal-Oriented Conversation with Dialogue Knowledge Transfer Networks

2019-10-03 · IJCNLP 2019 11 · Igor Shalyminov, Sungjin Lee, Arash Eshghi, Oliver Lemon

Goal-oriented dialogue systems are now being widely adopted in industry where it is of key importance to maintain a rapid prototyping cycle for new products and domains. Data-driven dialogue system development has to be …

Dialogue GenerationFew-Shot LearningGoal-Oriented Dialogue SystemsTransfer Learning