mlsanityData to 7 Oct 2026

Open-DDVM: A Reproduction and Extension of Diffusion Model for Optical Flow Estimation

arXiv 2312.01746 ↗First posted 4 Dec 2023cs.CVcited by 3

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Recently, Google proposes DDVM which for the first time demonstrates that a general diffusion model for image-to-image translation task works impressively well on optical flow estimation task without any specific designs like RAFT. However, DDVM is still a closed-source model with the expensive and private Palette-style pretraining. In this technical report, we present the first open-source DDVM by reproducing it. We study several design choices and find those important ones. By training on 40k public data with 4 GPUs, our reproduction achieves comparable performance to the closed-source DDVM. The code and model have been released in https://github.com/DQiaole/FlowDiffusion_pytorch.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 19 of its 23 references that are in the map. First posted on arXiv 4 Dec 2023.

Builds on

19 of 23 references.

References · 19

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  3. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  4. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  5. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  6. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  7. 2022Kubric: A scalable dataset generatorcited by 373
  8. 2017Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolationcited by 321
  9. 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 273
  10. 2021Learning to Estimate Hidden Motions with Global Motion Aggregationcited by 223
  11. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
  12. 2020Flow-edge Guided Video Completioncited by 104
7 more
  1. 2021AutoFlow: Learning a Better Training Set for Optical Flowcited by 102
  2. 2018Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimationcited by 94
  3. 2017Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognitioncited by 82
  4. 2022SKFlow: Learning Optical Flow with Super Kernelscited by 56
  5. 2022DIP: Deep Inverse Patchmatch for High-Resolution Optical Flowcited by 40
  6. 2023Rethinking Optical Flow from Geometric Matching Consistent Perspectivecited by 33
  7. 2022Disentangling Architecture and Training for Optical Flowcited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 283
  2. 2025Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Modelcited by 4
  3. 2026FlowPainter: Inpainting Optical Flow via Confidence-Guided Completioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Diffusion Model Translator for Efficient Image-to-Image Translation
  2. 2022Understanding DDPM Latent Codes Through Optimal Transport
  3. 2025Efficiency vs. Fidelity: A Comparative Analysis of Diffusion Probabilistic Models and Flow Matching on Low-Resource Hardware
  4. 2023MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance
  5. 2025Hierarchical Flow Diffusion for Efficient Frame Interpolation
  6. 2022Efficient Diffusion Models for Vision: A Survey
  7. 2024Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
  8. 2024Steering Rectified Flow Models in the Vector Field for Controlled Image Generation