The Midas Touch for Metric Depth
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909035223056384 |
|---|---|
| author | Ma, Yu Guo, Zizhan Xiong, Zuyi Zhang, Haoran Feng, Yi Zhao, Hongbo Wang, Hanli Fan, Rui |
| author_facet | Ma, Yu Guo, Zizhan Xiong, Zuyi Zhang, Haoran Feng, Yi Zhao, Hongbo Wang, Hanli Fan, Rui |
| contents | Recent advances have markedly improved the cross-scene generalization of relative depth estimation, yet its practical applicability remains limited by the absence of metric scale, local inconsistencies, and low computational efficiency. To address these issues, we present \emph{\textbf{M}idas \textbf{T}ouch for \textbf{D}epth} (MTD), a mathematically interpretable approach that converts relative depth into metric depth using only extremely sparse 3D data. To eliminate local scale inconsistencies, it applies a segment-wise recovery strategy via sparse graph optimization, followed by a pixel-wise refinement strategy using a discontinuity-aware geodesic cost. MTD exhibits strong generalization and achieves substantial accuracy improvements over previous depth completion and depth estimation methods. Moreover, its lightweight, plug-and-play design facilitates deployment and integration on diverse downstream 3D tasks. Project page is available at https://mias.group/MTD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11578 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Midas Touch for Metric Depth Ma, Yu Guo, Zizhan Xiong, Zuyi Zhang, Haoran Feng, Yi Zhao, Hongbo Wang, Hanli Fan, Rui Computer Vision and Pattern Recognition Recent advances have markedly improved the cross-scene generalization of relative depth estimation, yet its practical applicability remains limited by the absence of metric scale, local inconsistencies, and low computational efficiency. To address these issues, we present \emph{\textbf{M}idas \textbf{T}ouch for \textbf{D}epth} (MTD), a mathematically interpretable approach that converts relative depth into metric depth using only extremely sparse 3D data. To eliminate local scale inconsistencies, it applies a segment-wise recovery strategy via sparse graph optimization, followed by a pixel-wise refinement strategy using a discontinuity-aware geodesic cost. MTD exhibits strong generalization and achieves substantial accuracy improvements over previous depth completion and depth estimation methods. Moreover, its lightweight, plug-and-play design facilitates deployment and integration on diverse downstream 3D tasks. Project page is available at https://mias.group/MTD. |
| title | The Midas Touch for Metric Depth |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.11578 |