Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911859797393408 |
|---|---|
| author | Jun, Jinyoung Lee, Jae-Han Kim, Chang-Su |
| author_facet | Jun, Jinyoung Lee, Jae-Han Kim, Chang-Su |
| contents | The main function of depth completion is to compensate for an insufficient and unpredictable number of sparse depth measurements of hardware sensors. However, existing research on depth completion assumes that the sparsity -- the number of points or LiDAR lines -- is fixed for training and testing. Hence, the completion performance drops severely when the number of sparse depths changes significantly. To address this issue, we propose the sparsity-adaptive depth refinement (SDR) framework, which refines monocular depth estimates using sparse depth points. For SDR, we propose the masked spatial propagation network (MSPN) to perform SDR with a varying number of sparse depths effectively by gradually propagating sparse depth information throughout the entire depth map. Experimental results demonstrate that MPSN achieves state-of-the-art performance on both SDR and conventional depth completion scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_19294 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement Jun, Jinyoung Lee, Jae-Han Kim, Chang-Su Computer Vision and Pattern Recognition The main function of depth completion is to compensate for an insufficient and unpredictable number of sparse depth measurements of hardware sensors. However, existing research on depth completion assumes that the sparsity -- the number of points or LiDAR lines -- is fixed for training and testing. Hence, the completion performance drops severely when the number of sparse depths changes significantly. To address this issue, we propose the sparsity-adaptive depth refinement (SDR) framework, which refines monocular depth estimates using sparse depth points. For SDR, we propose the masked spatial propagation network (MSPN) to perform SDR with a varying number of sparse depths effectively by gradually propagating sparse depth information throughout the entire depth map. Experimental results demonstrate that MPSN achieves state-of-the-art performance on both SDR and conventional depth completion scenarios. |
| title | Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.19294 |