Guardado en:
Detalles Bibliográficos
Autores principales: Yu, Zhu, Zhao, Zhengyi, Zhang, Runmin, Qiu, Lingteng, Qiu, Kejie, He, Yisheng, Zhu, Siyu, Dong, Zilong, Cao, Si-Yuan, Shen, Hui-Liang
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.30115
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913170706137088
author Yu, Zhu
Zhao, Zhengyi
Zhang, Runmin
Qiu, Lingteng
Qiu, Kejie
He, Yisheng
Zhu, Siyu
Dong, Zilong
Cao, Si-Yuan
Shen, Hui-Liang
author_facet Yu, Zhu
Zhao, Zhengyi
Zhang, Runmin
Qiu, Lingteng
Qiu, Kejie
He, Yisheng
Zhu, Siyu
Dong, Zilong
Cao, Si-Yuan
Shen, Hui-Liang
contents This work presents the Large Depth Completion Model (LDCM), a simple, effective, and robust framework for single-view metric depth estimation with sparse observations. Without relying on complex architectural designs, LDCM generates metric-accurate dense depth maps using a transformer. It outperforms existing approaches across diverse datasets and sparse observations. We achieve this from two key perspectives: (1) leveraging existing monocular foundation models to improve the quality of sparse depth inputs, and (2) reformulating training objectives to better capture geometric structure and metric consistency. Specifically, a Poisson-based depth initialization strategy is first introduced to generate a uniform coarse dense depth map from diverse sparse observations, providing a strong structural prior for the network. Regarding the training objective, we replace the conventional depth head with a point map head that regresses per-pixel 3D coordinates in camera space, enabling the model to directly learn the underlying 3D scene structure instead of performing pixel-wise depth map restoration. Moreover, this design eliminates the need for camera intrinsic parameters, allowing LDCM to naturally produce metric-scaled 3D point maps. Extensive experiments demonstrate that LDCM consistently outperforms state-of-the-art methods across multiple benchmarks and varying sparsity levels in both depth completion and point map estimation, showcasing its effectiveness and strong generalization to unseen data distributions.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30115
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Large Depth Completion Model from Sparse Observations
Yu, Zhu
Zhao, Zhengyi
Zhang, Runmin
Qiu, Lingteng
Qiu, Kejie
He, Yisheng
Zhu, Siyu
Dong, Zilong
Cao, Si-Yuan
Shen, Hui-Liang
Computer Vision and Pattern Recognition
This work presents the Large Depth Completion Model (LDCM), a simple, effective, and robust framework for single-view metric depth estimation with sparse observations. Without relying on complex architectural designs, LDCM generates metric-accurate dense depth maps using a transformer. It outperforms existing approaches across diverse datasets and sparse observations. We achieve this from two key perspectives: (1) leveraging existing monocular foundation models to improve the quality of sparse depth inputs, and (2) reformulating training objectives to better capture geometric structure and metric consistency. Specifically, a Poisson-based depth initialization strategy is first introduced to generate a uniform coarse dense depth map from diverse sparse observations, providing a strong structural prior for the network. Regarding the training objective, we replace the conventional depth head with a point map head that regresses per-pixel 3D coordinates in camera space, enabling the model to directly learn the underlying 3D scene structure instead of performing pixel-wise depth map restoration. Moreover, this design eliminates the need for camera intrinsic parameters, allowing LDCM to naturally produce metric-scaled 3D point maps. Extensive experiments demonstrate that LDCM consistently outperforms state-of-the-art methods across multiple benchmarks and varying sparsity levels in both depth completion and point map estimation, showcasing its effectiveness and strong generalization to unseen data distributions.
title Large Depth Completion Model from Sparse Observations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.30115