mlsanityData to 7 Oct 2026

HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors

arXiv 2407.18443 ↗First posted 26 Jul 2024cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

We propose HYBRIDDEPTH, a robust depth estimation pipeline that addresses key challenges in depth estimation,including scale ambiguity, hardware heterogeneity, and generalizability. HYBRIDDEPTH leverages focal stack, data conveniently accessible in common mobile devices, to produce accurate metric depth maps. By incorporating depth priors afforded by recent advances in singleimage depth estimation, our model achieves a higher level of structural detail compared to existing methods. We test our pipeline as an end-to-end system, with a newly developed mobile client to capture focal stacks, which are then sent to a GPU-powered server for depth estimation. Comprehensive quantitative and qualitative analyses demonstrate that HYBRIDDEPTH outperforms state-of-the-art(SOTA) models on common datasets such as DDFF12 and NYU Depth V2. HYBRIDDEPTH also shows strong zero-shot generalization. When trained on NYU Depth V2, HYBRIDDEPTH surpasses SOTA models in zero-shot performance on ARKitScenes and delivers more structurally accurate depth maps on Mobile Depth. The code is available at https://github.com/cake-lab/HybridDepth/.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 26 Jul 2024.

Builds on

23 of 32 references.

References · 23

  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  3. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  4. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  5. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  6. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  7. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  8. 2023Unleashing Text-to-Image Diffusion Models for Visual Perceptioncited by 266
  9. 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 173
  10. 2023Towards Zero-Shot Scale-Aware Monocular Depth Estimationcited by 100
  11. 2022LocalBins: Improving Depth Estimation by Learning Local Distributionscited by 92
  12. 2024ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimationcited by 45
11 more
  1. 2021Toward Practical Monocular Indoor Depth Estimationcited by 42
  2. 2020Focus on defocus: bridging the synthetic to real domain gap for depth estimationcited by 37
  3. 2017Deep Depth From Focuscited by 28
  4. 2021Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervisioncited by 23
  5. 2021Deep Depth from Focus with Differential Focus Volumecited by 20
  6. 2023Monocular Visual-Inertial Depth Estimationcited by 18
  7. 2023Fully Self-Supervised Depth Estimation from Defocus Cluecited by 17
  8. 2014Variational Depth from Focus Reconstructioncited by 15
  9. 2022Learning Depth from Focus in the Wildcited by 8
  10. 2023DeepPointMap: Advancing LiDAR SLAM with Unified Neural Descriptorscited by 2
  11. 2024Attention and Sensory Processing in Augmented Reality: Empowering ADHD populationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 6.

11 papers.

  1. 2025Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Framescited by 3
  2. 2025HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Modelcited by 3
  3. 2025SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Referencecited by 1
  4. 2025DualFocus: Depth from Focus with Spatio-Focal Dual Variational Constraintscited by 1
  5. 2025AR as an Evaluation Playground: Bridging Metrics and Visual Perception of Computer Vision Modelscited by 0
  6. 2026SwiftNDC: Fast Neural Depth Correction for High-Fidelity 3D Reconstructioncited by 0
  7. 2026Long-Term Visual Localization in Dynamic Benthic Environments: A Dataset, Footprint-Based Ground Truth, and Visual Place Recognition Benchmarkcited by 0
  8. 2026Zero-Shot Depth from Defocuscited by 0
  9. 2026Towards Minimal Focal Stack in Shape from Focuscited by 0
  10. 2026Enhancing Hazy Wildlife Imagery: AnimalHaze3k and IncepDehazeGancited by 0
  11. 2026Enhancing Visual Perception in Foggy Conditions via Multiclass Fog Density Modelingcited by 0