mlsanityData to 14 Oct 2026

FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution

arXiv 2504.07093 ↗First posted 9 Apr 2025cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

A versatile video depth estimation model should (1) be accurate and consistent across frames, (2) produce high-resolution depth maps, and (3) support real-time streaming. We propose FlashDepth, a method that satisfies all three requirements, performing depth estimation on a 2044x1148 streaming video at 24 FPS. We show that, with careful modifications to pretrained single-image depth models, these capabilities are enabled with relatively little data and training. We evaluate our approach across multiple unseen datasets against state-of-the-art depth models, and find that ours outperforms them in terms of boundary sharpness and speed by a significant margin, while maintaining competitive accuracy. We hope our model will enable various applications that require high-resolution depth, such as video editing, and online decision-making, such as robotics. We release all code and model weights at https://github.com/Eyeline-Research/FlashDepth

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 61 of its 72 references that are in the map. First posted on arXiv 9 Apr 2025.

Builds on

61 of 72 references.

References · 61

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  7. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  8. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  9. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  10. 2021Vision Transformers for Dense Predictioncited by 1,803
  11. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  12. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
38 more
  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. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  4. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,336
  5. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  6. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  7. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  8. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  9. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  10. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  11. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  12. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  13. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  14. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
  15. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 365
  16. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 286
  17. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  18. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 276
  19. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  20. 2020Consistent Video Depth Estimationcited by 220
  21. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 216
  22. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 207
  23. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  24. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 205
  25. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 204
  26. 2025Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Controlcited by 185
  27. 2023Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereocited by 172
  28. 2024Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Predictioncited by 166
  29. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 148
  30. 2021SMD-Nets: Stereo Mixture Density Networkscited by 120
  31. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priorscited by 100
  32. 2024Align3R: Aligned Monocular Depth Estimation for Dynamic Videoscited by 79
  33. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 74
  34. 2020Don't Forget The Past: Recurrent Depth Estimation from Monocular Videocited by 71
  35. 2019Neural RGB->D Sensing: Depth and Uncertainty from a Video Cameracited by 69
  36. 2019Exploiting temporal consistency for real-time video depth estimationcited by 61
  37. 2024MegaScenes: Scene-Level View Synthesis at Scalecited by 58
  38. 2021Towards Real-Time Monocular Depth Estimation for Robotics: A Surveycited by 57

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 10.

14 papers.

Sort:

By area:

  1. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 170
  2. 2026Vista4D: Video Reshooting with 4D Point Cloudscited by 18
  3. 2025Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimationcited by 10
  4. 2026DVD: Deterministic Video Depth Estimation with Generative Priorscited by 4
  5. 2026DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimationcited by 3
  6. 2026Stabilizing Streaming Video Geometry via Dynamic Feature Normalizationcited by 3
  7. 2026Towards Consistent Video Geometry Estimationcited by 3
  8. 2025EndoStreamDepth: Temporally Consistent Monocular Depth Estimation for Endoscopic Video Streamscited by 2
  9. 2026StableDPT: Temporal Stable Monocular Video Depth Estimationcited by 2
  10. 2026Pixel-Perfect Visual Geometry Estimationcited by 2
  11. 2025Online Video Depth Anything: Temporally-Consistent Depth Prediction with Low Memory Consumptioncited by 0
  12. 2026AsyncMDE: Real-Time Monocular Depth Estimation via Asynchronous Spatial Memorycited by 0
2 more
  1. 2026GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depthcited by 0
  2. 2026Monocular Depth Estimation from a Single Image: Progress and Opportunitiescited by 0