DepthLab: From Partial to Complete
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914394090242048 |
|---|---|
| author | Liu, Zhiheng Cheng, Ka Leong Wang, Qiuyu Wang, Shuzhe Ouyang, Hao Tan, Bin Zhu, Kai Shen, Yujun Chen, Qifeng Luo, Ping |
| author_facet | Liu, Zhiheng Cheng, Ka Leong Wang, Qiuyu Wang, Shuzhe Ouyang, Hao Tan, Bin Zhu, Kai Shen, Yujun Chen, Qifeng Luo, Ping |
| contents | Missing values remain a common challenge for depth data across its wide range of applications, stemming from various causes like incomplete data acquisition and perspective alteration. This work bridges this gap with DepthLab, a foundation depth inpainting model powered by image diffusion priors. Our model features two notable strengths: (1) it demonstrates resilience to depth-deficient regions, providing reliable completion for both continuous areas and isolated points, and (2) it faithfully preserves scale consistency with the conditioned known depth when filling in missing values. Drawing on these advantages, our approach proves its worth in various downstream tasks, including 3D scene inpainting, text-to-3D scene generation, sparse-view reconstruction with DUST3R, and LiDAR depth completion, exceeding current solutions in both numerical performance and visual quality. Our project page with source code is available at https://johanan528.github.io/depthlab_web/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18153 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DepthLab: From Partial to Complete Liu, Zhiheng Cheng, Ka Leong Wang, Qiuyu Wang, Shuzhe Ouyang, Hao Tan, Bin Zhu, Kai Shen, Yujun Chen, Qifeng Luo, Ping Computer Vision and Pattern Recognition Missing values remain a common challenge for depth data across its wide range of applications, stemming from various causes like incomplete data acquisition and perspective alteration. This work bridges this gap with DepthLab, a foundation depth inpainting model powered by image diffusion priors. Our model features two notable strengths: (1) it demonstrates resilience to depth-deficient regions, providing reliable completion for both continuous areas and isolated points, and (2) it faithfully preserves scale consistency with the conditioned known depth when filling in missing values. Drawing on these advantages, our approach proves its worth in various downstream tasks, including 3D scene inpainting, text-to-3D scene generation, sparse-view reconstruction with DUST3R, and LiDAR depth completion, exceeding current solutions in both numerical performance and visual quality. Our project page with source code is available at https://johanan528.github.io/depthlab_web/. |
| title | DepthLab: From Partial to Complete |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.18153 |