OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913919697682432 |
|---|---|
| author | Zuo, Yiming Yang, Willow Ma, Zeyu Deng, Jia |
| author_facet | Zuo, Yiming Yang, Willow Ma, Zeyu Deng, Jia |
| contents | Depth completion (DC) aims to predict a dense depth map from an RGB image and a sparse depth map. Existing DC methods generalize poorly to new datasets or unseen sparse depth patterns, limiting their real-world applications. We propose OMNI-DC, a highly robust DC model that generalizes well zero-shot to various datasets. The key design is a novel Multi-resolution Depth Integrator, allowing our model to deal with very sparse depth inputs. We also introduce a novel Laplacian loss to model the ambiguity in the training process. Moreover, we train OMNI-DC on a mixture of high-quality datasets with a scale normalization technique and synthetic depth patterns. Extensive experiments on 7 datasets show consistent improvements over baselines, reducing errors by as much as 43%. Codes and checkpoints are available at https://github.com/princeton-vl/OMNI-DC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_19278 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration Zuo, Yiming Yang, Willow Ma, Zeyu Deng, Jia Computer Vision and Pattern Recognition Depth completion (DC) aims to predict a dense depth map from an RGB image and a sparse depth map. Existing DC methods generalize poorly to new datasets or unseen sparse depth patterns, limiting their real-world applications. We propose OMNI-DC, a highly robust DC model that generalizes well zero-shot to various datasets. The key design is a novel Multi-resolution Depth Integrator, allowing our model to deal with very sparse depth inputs. We also introduce a novel Laplacian loss to model the ambiguity in the training process. Moreover, we train OMNI-DC on a mixture of high-quality datasets with a scale normalization technique and synthetic depth patterns. Extensive experiments on 7 datasets show consistent improvements over baselines, reducing errors by as much as 43%. Codes and checkpoints are available at https://github.com/princeton-vl/OMNI-DC. |
| title | OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.19278 |