HDCNet: A Hybrid Depth Completion Network for Grasping Transparent and Reflective Objects
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917070932803584 |
|---|---|
| author | Xie, Guanghu Li, Mingxu Wu, Songwei Liu, Yang Xie, Zongwu Cao, Baoshi Liu, Hong |
| author_facet | Xie, Guanghu Li, Mingxu Wu, Songwei Liu, Yang Xie, Zongwu Cao, Baoshi Liu, Hong |
| contents | Depth perception of transparent and reflective objects has long been a critical challenge in robotic manipulation.Conventional depth sensors often fail to provide reliable measurements on such surfaces, limiting the performance of robots in perception and grasping tasks. To address this issue, we propose a novel depth completion network,HDCNet,which integrates the complementary strengths of Transformer,CNN and Mamba architectures.Specifically,the encoder is designed as a dual-branch Transformer-CNN framework to extract modality-specific features. At the shallow layers of the encoder, we introduce a lightweight multimodal fusion module to effectively integrate low-level features. At the network bottleneck,a Transformer-Mamba hybrid fusion module is developed to achieve deep integration of high-level semantic and global contextual information, significantly enhancing depth completion accuracy and robustness. Extensive evaluations on multiple public datasets demonstrate that HDCNet achieves state-of-the-art(SOTA) performance in depth completion tasks.Furthermore,robotic grasping experiments show that HDCNet substantially improves grasp success rates for transparent and reflective objects,achieving up to a 60% increase. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_07081 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HDCNet: A Hybrid Depth Completion Network for Grasping Transparent and Reflective Objects Xie, Guanghu Li, Mingxu Wu, Songwei Liu, Yang Xie, Zongwu Cao, Baoshi Liu, Hong Robotics Depth perception of transparent and reflective objects has long been a critical challenge in robotic manipulation.Conventional depth sensors often fail to provide reliable measurements on such surfaces, limiting the performance of robots in perception and grasping tasks. To address this issue, we propose a novel depth completion network,HDCNet,which integrates the complementary strengths of Transformer,CNN and Mamba architectures.Specifically,the encoder is designed as a dual-branch Transformer-CNN framework to extract modality-specific features. At the shallow layers of the encoder, we introduce a lightweight multimodal fusion module to effectively integrate low-level features. At the network bottleneck,a Transformer-Mamba hybrid fusion module is developed to achieve deep integration of high-level semantic and global contextual information, significantly enhancing depth completion accuracy and robustness. Extensive evaluations on multiple public datasets demonstrate that HDCNet achieves state-of-the-art(SOTA) performance in depth completion tasks.Furthermore,robotic grasping experiments show that HDCNet substantially improves grasp success rates for transparent and reflective objects,achieving up to a 60% increase. |
| title | HDCNet: A Hybrid Depth Completion Network for Grasping Transparent and Reflective Objects |
| topic | Robotics |
| url | https://arxiv.org/abs/2511.07081 |