SteeredMarigold: Steering Diffusion Towards Depth Completion of Largely Incomplete Depth Maps
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_ | 1866910844740173824 |
|---|---|
| author | Gregorek, Jakub Nalpantidis, Lazaros |
| author_facet | Gregorek, Jakub Nalpantidis, Lazaros |
| contents | Even if the depth maps captured by RGB-D sensors deployed in real environments are often characterized by large areas missing valid depth measurements, the vast majority of depth completion methods still assumes depth values covering all areas of the scene. To address this limitation, we introduce SteeredMarigold, a training-free, zero-shot depth completion method capable of producing metric dense depth, even for largely incomplete depth maps. SteeredMarigold achieves this by using the available sparse depth points as conditions to steer a denoising diffusion probabilistic model. Our method outperforms relevant top-performing methods on the NYUv2 dataset, in tests where no depth was provided for a large area, achieving state-of-art performance and exhibiting remarkable robustness against depth map incompleteness. Our source code is publicly available at https://steeredmarigold.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10202 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SteeredMarigold: Steering Diffusion Towards Depth Completion of Largely Incomplete Depth Maps Gregorek, Jakub Nalpantidis, Lazaros Robotics Computer Vision and Pattern Recognition Even if the depth maps captured by RGB-D sensors deployed in real environments are often characterized by large areas missing valid depth measurements, the vast majority of depth completion methods still assumes depth values covering all areas of the scene. To address this limitation, we introduce SteeredMarigold, a training-free, zero-shot depth completion method capable of producing metric dense depth, even for largely incomplete depth maps. SteeredMarigold achieves this by using the available sparse depth points as conditions to steer a denoising diffusion probabilistic model. Our method outperforms relevant top-performing methods on the NYUv2 dataset, in tests where no depth was provided for a large area, achieving state-of-art performance and exhibiting remarkable robustness against depth map incompleteness. Our source code is publicly available at https://steeredmarigold.github.io. |
| title | SteeredMarigold: Steering Diffusion Towards Depth Completion of Largely Incomplete Depth Maps |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.10202 |