mlsanityData to 14 Oct 2026

PTC-Depth: Pose-Refined Monocular Depth Estimation with Temporal Consistency

arXiv 2604.01791 ↗First posted 2 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Monocular depth estimation (MDE) has been widely adopted in the perception systems of autonomous vehicles and mobile robots. However, existing approaches often struggle to maintain temporal consistency in depth estimation across consecutive frames. This inconsistency not only causes jitter but can also lead to estimation failures when the depth range changes abruptly. To address these challenges, this paper proposes a consistency-aware monocular depth estimation framework that leverages wheel odometry from a mobile robot to achieve stable and coherent depth predictions over time. Specifically, we estimate camera pose and sparse depth from triangulation using optical flow between consecutive frames. The sparse depth estimates are used to update a recursive Bayesian estimate of the metric scale, which is then applied to rescale the relative depth predicted by a pre-trained depth estimation foundation model. The proposed method is evaluated on the KITTI, TartanAir, MS2, and our own dataset, demonstrating robust and accurate depth estimation performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 51 references that are in the map. First posted on arXiv 2 Apr 2026.

Builds on

35 of 51 references.

References · 35

  1. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  2. 2024Depth Anything V2cited by 1,422
  3. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  4. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  5. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  6. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  7. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 382
  8. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 365
  9. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 207
  10. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  11. 2020Robust Consistent Video Depth Estimationcited by 188
  12. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 161
23 more
  1. 2025Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysiscited by 78
  2. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 74
  3. 2016Fast Optical Flow using Dense Inverse Searchcited by 71
  4. 2019Exploiting temporal consistency for real-time video depth estimationcited by 61
  5. 2021360MonoDepth: High-Resolution 360deg Monocular Depth Estimationcited by 60
  6. 2024Depth Any Video with Scalable Synthetic Datacited by 57
  7. 2024Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusioncited by 50
  8. 2021Toward Practical Monocular Indoor Depth Estimationcited by 42
  9. 2024Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Drivingcited by 32
  10. 2022Learning Optical Flow, Depth, and Scene Flow without Real-World Labelscited by 31
  11. 2024Video Depth without Video Modelscited by 29
  12. 2018Deep Convolutional Compressed Sensing for LiDAR Depth Completioncited by 27
  13. 2022UDepth: Fast Monocular Depth Estimation for Visually-guided Underwater Robotscited by 27
  14. 2024DepthLab: From Partial to Completecited by 27
  15. 2024SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillationcited by 21
  16. 2023Monocular Visual-Inertial Depth Estimationcited by 18
  17. 2023Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalizationcited by 18
  18. 2025Relative Pose Estimation through Affine Corrections of Monocular Depth Priorscited by 18
  19. 2023SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via Swin Transformer and Densely Cascaded Networkcited by 10
  20. 2025RePoseD: Efficient Relative Pose Estimation With Known Depth Informationcited by 10
  21. 2024SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimationcited by 8
  22. 2024Fieldscale: Locality-Aware Field-based Adaptive Rescaling for Thermal Infrared Imagecited by 8
  23. 2024A Simple yet Effective Test-Time Adaptation for Zero-Shot Monocular Metric Depth Estimationcited by 6

Built on by

Not cited yet.