mlsanityData to 14 Oct 2026

DuCos: Duality Constrained Depth Super-Resolution via Foundation Model

arXiv 2503.04171 ↗First posted 6 Mar 2025cs.CVcited by 11

Not on the map. Why?

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.

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

47 of 65 references.

References · 47

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Convex optimizationcited by 2,515
  3. 2024Depth Anything V2cited by 1,422
  4. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  5. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  6. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  7. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
  8. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 382
  9. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 365
  10. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 353
  11. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 173
  12. 2019Pixel-Adaptive Convolutional Neural Networkscited by 126
35 more
  1. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 118
  2. 2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
  3. 2019Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusioncited by 79
  4. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 74
  5. 2021Discrete Cosine Transform Network for Guided Depth Map Super-Resolutioncited by 71
  6. 2021Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baselinecited by 61
  7. 2019Deformable Kernel Networks for Joint Image Filteringcited by 59
  8. 2017Joint Image Filtering with Deep Convolutional Networkscited by 52
  9. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 52
  10. 2024Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusioncited by 50
  11. 2022Guided Depth Super-Resolution by Deep Anisotropic Diffusioncited by 46
  12. 2024Tri-Perspective View Decomposition for Geometry-Aware Depth Completioncited by 42
  13. 2021BridgeNet: A Joint Learning Network of Depth Map Super-Resolution and Monocular Depth Estimationcited by 31
  14. 2021Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolutioncited by 30
  15. 2023Spherical Space Feature Decomposition for Guided Depth Map Super-Resolutioncited by 28
  16. 2022Learning Graph Regularisation for Guided Super-Resolutioncited by 27
  17. 2023SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-Resolutioncited by 27
  18. 2024DepthLab: From Partial to Completecited by 27
  19. 2024Depth Prompting for Sensor-Agnostic Depth Estimationcited by 26
  20. 2016ATGV-Net: Accurate Depth Super-Resolutioncited by 22
  21. 2023Symmetric Uncertainty-Aware Feature Transmission for Depth Super-Resolutioncited by 19
  22. 2021Deep Attentional Guided Image Filteringcited by 17
  23. 2024Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flowcited by 15
  24. 2023Structure Flow-Guided Network for Real Depth Super-Resolutioncited by 14
  25. 2024DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolutioncited by 14
  26. 2024Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completioncited by 12
  27. 2023RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completioncited by 11
  28. 2023Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flowcited by 9
  29. 2025C2PD: Continuity-Constrained Pixelwise Deformation for Guided Depth Super-Resolutioncited by 8
  30. 2022Learning Continuous Depth Representation via Geometric Spatial Aggregatorcited by 7
  31. 2024Decoupling Fine Detail and Global Geometry for Compressed Depth Map Super-Resolutioncited by 6
  32. 2024A Simple yet Effective Test-Time Adaptation for Zero-Shot Monocular Metric Depth Estimationcited by 6
  33. 2024Scene Prior Filtering for Depth Super-Resolutioncited by 5
  34. 2024Adverse Weather Optical Flow: Cumulative Homogeneous-Heterogeneous Adaptationcited by 4
  35. 2024Learning Hierarchical Color Guidance for Depth Map Super-Resolutioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 8.

11 papers.

  1. 2025SpatioTemporal Difference Network for Video Depth Super-Resolutioncited by 4
  2. 2026Large Depth Completion Model from Sparse Observationscited by 4
  3. 2025See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Predictioncited by 3
  4. 2025Multi-Order Matching Network for Alignment-Free Depth Super-Resolutioncited by 1
  5. 2026NAIMA: Semantics Aware RGB Guided Depth Super-Resolutioncited by 1
  6. 2026Robust Depth Super-Resolution via Adaptive Diffusion Samplingcited by 0
  7. 2026Robust Self-Supervised Cross-Modal Super-Resolution against Real-World Misaligned Observationscited by 0
  8. 2026DegBins: Degradation-Driven Binning for Depth Super-Resolutioncited by 0
  9. 2026Interactive State Space Model with Cross-Modal Local Scanning for Depth Super-Resolutioncited by 0
  10. 2026WAVE: Reversing the Guidance Hierarchy for Coarse-to-Fine Guided Depth Super-Resolutioncited by 0
  11. 2026FoundDSR: A Generalizable Foundation Model with Guided 2D Gaussian Splatting for Depth Super-Resolutioncited by 0