The Devil is in the Details: Boosting Guided Depth Super-Resolution via Rethinking Cross-Modal Alignment and Aggregation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929210474364928 |
|---|---|
| author | Jiang, Xinni Kuang, Zengsheng Guo, Chunle Zhang, Ruixun Cai, Lei Fan, Xiao Li, Chongyi |
| author_facet | Jiang, Xinni Kuang, Zengsheng Guo, Chunle Zhang, Ruixun Cai, Lei Fan, Xiao Li, Chongyi |
| contents | Guided depth super-resolution (GDSR) involves restoring missing depth details using the high-resolution RGB image of the same scene. Previous approaches have struggled with the heterogeneity and complementarity of the multi-modal inputs, and neglected the issues of modal misalignment, geometrical misalignment, and feature selection. In this study, we rethink some essential components in GDSR networks and propose a simple yet effective Dynamic Dual Alignment and Aggregation network (D2A2). D2A2 mainly consists of 1) a dynamic dual alignment module that adapts to alleviate the modal misalignment via a learnable domain alignment block and geometrically align cross-modal features by learning the offset; and 2) a mask-to-pixel feature aggregate module that uses the gated mechanism and pixel attention to filter out irrelevant texture noise from RGB features and combine the useful features with depth features. By combining the strengths of RGB and depth features while minimizing disturbance introduced by the RGB image, our method with simple reuse and redesign of basic components achieves state-of-the-art performance on multiple benchmark datasets. The code is available at https://github.com/JiangXinni/D2A2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08123 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Devil is in the Details: Boosting Guided Depth Super-Resolution via Rethinking Cross-Modal Alignment and Aggregation Jiang, Xinni Kuang, Zengsheng Guo, Chunle Zhang, Ruixun Cai, Lei Fan, Xiao Li, Chongyi Computer Vision and Pattern Recognition Guided depth super-resolution (GDSR) involves restoring missing depth details using the high-resolution RGB image of the same scene. Previous approaches have struggled with the heterogeneity and complementarity of the multi-modal inputs, and neglected the issues of modal misalignment, geometrical misalignment, and feature selection. In this study, we rethink some essential components in GDSR networks and propose a simple yet effective Dynamic Dual Alignment and Aggregation network (D2A2). D2A2 mainly consists of 1) a dynamic dual alignment module that adapts to alleviate the modal misalignment via a learnable domain alignment block and geometrically align cross-modal features by learning the offset; and 2) a mask-to-pixel feature aggregate module that uses the gated mechanism and pixel attention to filter out irrelevant texture noise from RGB features and combine the useful features with depth features. By combining the strengths of RGB and depth features while minimizing disturbance introduced by the RGB image, our method with simple reuse and redesign of basic components achieves state-of-the-art performance on multiple benchmark datasets. The code is available at https://github.com/JiangXinni/D2A2. |
| title | The Devil is in the Details: Boosting Guided Depth Super-Resolution via Rethinking Cross-Modal Alignment and Aggregation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.08123 |