mlsanityData to 14 Oct 2026

FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases

arXiv 2509.05297 ↗First posted 5 Sep 2025cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

We present FlowSeek, a novel framework for optical flow requiring minimal hardware resources for training. FlowSeek marries the latest advances on the design space of optical flow networks with cutting-edge single-image depth foundation models and classical low-dimensional motion parametrization, implementing a compact, yet accurate architecture. FlowSeek is trained on a single consumer-grade GPU, a hardware budget about 8x lower compared to most recent methods, and still achieves superior cross-dataset generalization on Sintel Final and KITTI, with a relative improvement of 10 and 15% over the previous state-of-the-art SEA-RAFT, as well as on Spring and LayeredFlow datasets.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 70 of its 95 references that are in the map. First posted on arXiv 5 Sep 2025.

Builds on

70 of 95 references.

References · 70

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  7. 2021Vision Transformers for Dense Predictioncited by 1,803
  8. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  9. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  10. 2024Depth Anything V2cited by 1,422
  11. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  12. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
38 more
  1. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  2. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  3. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  4. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
  5. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  6. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  7. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  8. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  9. 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 424
  10. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  11. 2018YouTube-VOS: A Large-Scale Video Object Segmentation Benchmarkcited by 383
  12. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 346
  13. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 327
  14. 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 275
  15. 2022Unifying Flow, Stereo and Depth Estimationcited by 275
  16. 2021Learning to Estimate Hidden Motions with Global Motion Aggregationcited by 224
  17. 2023Tracking Everything Everywhere All at Oncecited by 193
  18. 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 174
  19. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 173
  20. 2023Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereocited by 172
  21. 2017Playing for Benchmarkscited by 169
  22. 2019Quadratic video interpolationcited by 145
  23. 2020What Matters in Unsupervised Optical Flowcited by 124
  24. 2020Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimationcited by 120
  25. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
  26. 2023FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimationcited by 114
  27. 2021AutoFlow: Learning a Better Training Set for Optical Flowcited by 102
  28. 2018Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimationcited by 94
  29. 2017Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognitioncited by 82
  30. 2022CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flowcited by 82
  31. 2023VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimationcited by 82
  32. 2015EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flowcited by 80
  33. 2019A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularizationcited by 76
  34. 2022Global Matching with Overlapping Attention for Optical Flow Estimationcited by 64
  35. 2022SKFlow: Learning Optical Flow with Super Kernelscited by 56
  36. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 52
  37. 2020Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimationcited by 49
  38. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 47

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 9.

10 papers.

  1. 2026CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registrationcited by 3
  2. 2025Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learningcited by 1
  3. 2026Triangular Consistency as a Universal Constraint for Learning Optical Flowcited by 1
  4. 2026DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Modelscited by 0
  5. 2026FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flowcited by 0
  6. 2026Rethinking Dense Optical Flow without Test-Time Scalingcited by 0
  7. 2026UniRED: Unified RGB-D Video Frame Interpolation with Event Guidancecited by 0
  8. 2026Every Step of the Way: Video-based Parkinsonian Turning Step Countingcited by 0
  9. 2026FlowPainter: Inpainting Optical Flow via Confidence-Guided Completioncited by 0
  10. 2026Glass Surface Detection Grounded in 3D Visual Geometrycited by 0