mlsanityData to 7 Oct 2026

Online Video Depth Anything: Temporally-Consistent Depth Prediction with Low Memory Consumption

arXiv 2510.09182 ↗First posted 10 Oct 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Depth estimation from monocular video has become a key component of many real-world computer vision systems. Recently, Video Depth Anything (VDA) has demonstrated strong performance on long video sequences. However, it relies on batch-processing which prohibits its use in an online setting. In this work, we overcome this limitation and introduce online VDA (oVDA). The key innovation is to employ techniques from Large Language Models (LLMs), namely, caching latent features during inference and masking frames at training. Our oVDA method outperforms all competing online video depth estimation methods in both accuracy and VRAM usage. Low VRAM usage is particularly important for deployment on edge devices. We demonstrate that oVDA runs at 42 FPS on an NVIDIA A100 and at 20 FPS on an NVIDIA Jetson edge device. We will release both, code and compilation scripts, making oVDA easy to deploy on low-power hardware.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 47 of its 55 references that are in the map. First posted on arXiv 10 Oct 2025.

Builds on

47 of 55 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  4. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  5. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  7. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  8. 2024Depth Anything V2cited by 1,385
  9. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  10. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,283
  11. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  12. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
35 more
  1. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 942
  2. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  3. 2022Efficiently Scaling Transformer Inferencecited by 529
  4. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  5. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  6. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  7. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  8. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 283
  9. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 274
  10. 2020Consistent Video Depth Estimationcited by 220
  11. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  12. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 202
  13. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 202
  14. 2020Robust Consistent Video Depth Estimationcited by 188
  15. 2019ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residualscited by 180
  16. 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 173
  17. 2025Streaming 4D Visual Geometry Transformercited by 147
  18. 2024MiniCache: KV Cache Compression in Depth Dimension for Large Language Modelscited by 122
  19. 2014Deep Convolutional Neural Fields for Depth Estimation from a Single Imagecited by 106
  20. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priorscited by 100
  21. 2024Align3R: Aligned Monocular Depth Estimation for Dynamic Videoscited by 79
  22. 2020Don't Forget The Past: Recurrent Depth Estimation from Monocular Videocited by 71
  23. 2019Exploiting temporal consistency for real-time video depth estimationcited by 61
  24. 2024Depth Any Video with Scalable Synthetic Datacited by 57
  25. 2021Consistent Depth of Moving Objects in Videocited by 56
  26. 2024Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videoscited by 48
  27. 2021Single Image Depth Estimation: An Overviewcited by 35
  28. 2024Video Depth without Video Modelscited by 28
  29. 2021Temporally Consistent Online Depth Estimation in Dynamic Scenescited by 26
  30. 2023MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimationcited by 24
  31. 2025FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolutioncited by 14
  32. 2019IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimationcited by 12
  33. 2023Temporally Consistent Online Depth Estimation Using Point-Based Fusioncited by 12
  34. 2024PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimagecited by 11
  35. 2025DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimationcited by 2

Built on by

Not cited yet.