DuCos: Duality Constrained Depth Super-Resolution via Foundation Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Zhiqiang, Wang, Zhengxue, Dong, Haoye, Li, Jun, Yang, Jian, Lee, Gim Hee
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916909615677440
author Yan, Zhiqiang
Wang, Zhengxue
Dong, Haoye
Li, Jun
Yang, Jian
Lee, Gim Hee
author_facet Yan, Zhiqiang
Wang, Zhengxue
Dong, Haoye
Li, Jun
Yang, Jian
Lee, Gim Hee
contents We introduce DuCos, a novel depth super-resolution framework grounded in Lagrangian duality theory, offering a flexible integration of multiple constraints and reconstruction objectives to enhance accuracy and robustness. Our DuCos is the first to significantly improve generalization across diverse scenarios with foundation models as prompts. The prompt design consists of two key components: Correlative Fusion (CF) and Gradient Regulation (GR). CF facilitates precise geometric alignment and effective fusion between prompt and depth features, while GR refines depth predictions by enforcing consistency with sharp-edged depth maps derived from foundation models. Crucially, these prompts are seamlessly embedded into the Lagrangian constraint term, forming a synergistic and principled framework. Extensive experiments demonstrate that DuCos outperforms existing state-of-the-art methods, achieving superior accuracy, robustness, and generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2503_04171
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DuCos: Duality Constrained Depth Super-Resolution via Foundation Model
Yan, Zhiqiang
Wang, Zhengxue
Dong, Haoye
Li, Jun
Yang, Jian
Lee, Gim Hee
Computer Vision and Pattern Recognition
We introduce DuCos, a novel depth super-resolution framework grounded in Lagrangian duality theory, offering a flexible integration of multiple constraints and reconstruction objectives to enhance accuracy and robustness. Our DuCos is the first to significantly improve generalization across diverse scenarios with foundation models as prompts. The prompt design consists of two key components: Correlative Fusion (CF) and Gradient Regulation (GR). CF facilitates precise geometric alignment and effective fusion between prompt and depth features, while GR refines depth predictions by enforcing consistency with sharp-edged depth maps derived from foundation models. Crucially, these prompts are seamlessly embedded into the Lagrangian constraint term, forming a synergistic and principled framework. Extensive experiments demonstrate that DuCos outperforms existing state-of-the-art methods, achieving superior accuracy, robustness, and generalization.
title DuCos: Duality Constrained Depth Super-Resolution via Foundation Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.04171