# DuCos: Duality Constrained Depth Super-Resolution via Foundation Model

arXiv: https://arxiv.org/abs/2503.04171 · HTML: https://mlsanity.com/paper/2503.04171/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 65 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 30 of 47)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation](https://mlsanity.com/paper/2404.15506/) (2024)
- [UniDepth: Universal Monocular Metric Depth Estimation](https://mlsanity.com/paper/2403.18913/) (2024)
- [Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image](https://mlsanity.com/paper/2307.10984/) (2023)
- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [FoundationStereo: Zero-Shot Stereo Matching](https://mlsanity.com/paper/2501.09898/) (2025)
- [Pixel-Adaptive Convolutional Neural Networks](https://mlsanity.com/paper/1904.05373/) (2019)
- [DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation](https://mlsanity.com/paper/2203.14211/) (2022)
- [RigNet: Repetitive Image Guided Network for Depth Completion](https://mlsanity.com/paper/2107.13802/) (2021)
- [Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusion](https://mlsanity.com/paper/1910.04066/) (2019)
- [Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation](https://mlsanity.com/paper/2412.14015/) (2024)
- [Discrete Cosine Transform Network for Guided Depth Map Super-Resolution](https://mlsanity.com/paper/2104.06977/) (2021)
- [Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline](https://mlsanity.com/paper/2104.06174/) (2021)
- [Deformable Kernel Networks for Joint Image Filtering](https://mlsanity.com/paper/1910.08373/) (2019)
- [Joint Image Filtering with Deep Convolutional Networks](https://mlsanity.com/paper/1710.04200/) (2017)
- [DEFOM-Stereo: Depth Foundation Model Based Stereo Matching](https://mlsanity.com/paper/2501.09466/) (2025)
- [Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion](https://mlsanity.com/paper/2412.13389/) (2024)
- [Guided Depth Super-Resolution by Deep Anisotropic Diffusion](https://mlsanity.com/paper/2211.11592/) (2022)
- [Tri-Perspective View Decomposition for Geometry-Aware Depth Completion](https://mlsanity.com/paper/2403.15008/) (2024)
- [BridgeNet: A Joint Learning Network of Depth Map Super-Resolution and Monocular Depth Estimation](https://mlsanity.com/paper/2107.12541/) (2021)
- [Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution](https://mlsanity.com/paper/2103.12955/) (2021)
- [Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution](https://mlsanity.com/paper/2303.08942/) (2023)
- [Learning Graph Regularisation for Guided Super-Resolution](https://mlsanity.com/paper/2203.14297/) (2022)
- [SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-Resolution](https://mlsanity.com/paper/2312.05799/) (2023)
- [DepthLab: From Partial to Complete](https://mlsanity.com/paper/2412.18153/) (2024)

## Built on by (most cited first, 11 of 11)

- [SpatioTemporal Difference Network for Video Depth Super-Resolution](https://mlsanity.com/paper/2508.01259/) (2025)
- [Large Depth Completion Model from Sparse Observations](https://mlsanity.com/paper/2605.30115/) (2026)
- [See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction](https://mlsanity.com/paper/2505.20641/) (2025)
- [Multi-Order Matching Network for Alignment-Free Depth Super-Resolution](https://mlsanity.com/paper/2511.16361/) (2025)
- [NAIMA: Semantics Aware RGB Guided Depth Super-Resolution](https://mlsanity.com/paper/2604.04407/) (2026)
- [Robust Depth Super-Resolution via Adaptive Diffusion Sampling](https://mlsanity.com/paper/2602.09510/) (2026)
- [Robust Self-Supervised Cross-Modal Super-Resolution against Real-World Misaligned Observations](https://mlsanity.com/paper/2602.18822/) (2026)
- [DegBins: Degradation-Driven Binning for Depth Super-Resolution](https://mlsanity.com/paper/2605.09628/) (2026)
- [Interactive State Space Model with Cross-Modal Local Scanning for Depth Super-Resolution](https://mlsanity.com/paper/2605.11934/) (2026)
- [WAVE: Reversing the Guidance Hierarchy for Coarse-to-Fine Guided Depth Super-Resolution](https://mlsanity.com/paper/2608.25302/) (2026)
- [FoundDSR: A Generalizable Foundation Model with Guided 2D Gaussian Splatting for Depth Super-Resolution](https://mlsanity.com/paper/2609.32323/) (2026)

## Abstract (arXiv)

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.