# Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images

arXiv: https://arxiv.org/abs/2506.07740 · HTML: https://mlsanity.com/paper/2506.07740/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 93 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 30 of 44)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes](https://mlsanity.com/paper/2011.13084/) (2020)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Dynamic View Synthesis from Dynamic Monocular Video](https://mlsanity.com/paper/2105.06468/) (2021)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [Single-View View Synthesis with Multiplane Images](https://mlsanity.com/paper/2004.11364/) (2020)
- [TAP-Vid: A Benchmark for Tracking Any Point in a Video](https://mlsanity.com/paper/2211.03726/) (2022)
- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow](https://mlsanity.com/paper/2405.14793/) (2024)
- [FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing](https://mlsanity.com/paper/2310.05922/) (2023)
- [SelFlow: Self-Supervised Learning of Optical Flow](https://mlsanity.com/paper/1904.09117/) (2019)
- [What Matters in Unsupervised Optical Flow](https://mlsanity.com/paper/2006.04902/) (2020)
- [Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation](https://mlsanity.com/paper/2003.13045/) (2020)
- [TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut](https://mlsanity.com/paper/2209.00383/) (2022)
- [Geometry-Free View Synthesis: Transformers and no 3D Priors](https://mlsanity.com/paper/2104.07652/) (2021)
- [PixelSynth: Generating a 3D-Consistent Experience from a Single Image](https://mlsanity.com/paper/2108.05892/) (2021)
- [CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow](https://mlsanity.com/paper/2203.16896/) (2022)
- [SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping](https://mlsanity.com/paper/2105.07014/) (2021)
- [Physics-based Noise Modeling for Extreme Low-light Photography](https://mlsanity.com/paper/2108.02158/) (2021)
- [DDFlow: Learning Optical Flow with Unlabeled Data Distillation](https://mlsanity.com/paper/1902.09145/) (2019)

## Built on by (most cited first, 9 of 9)

- [NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results](https://mlsanity.com/paper/2604.14816/) (2026)
- [Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space](https://mlsanity.com/paper/2507.00392/) (2025)
- [PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models](https://mlsanity.com/paper/2507.08400/) (2025)
- [Rethinking Unsupervised Cross-modal Flow Estimation: Learning from Decoupled Optimization and Consistency Constraint](https://mlsanity.com/paper/2509.24423/) (2025)
- [HiSC: Hierarchical Spatial Clustering Token Compression for Efficient 3D Scene Understanding](https://mlsanity.com/paper/2608.04610/) (2026)
- [Boosting Text-Driven Video Segmentation via Geometry-Aware Distillation](https://mlsanity.com/paper/2606.24464/) (2026)
- [On the Real-World Generalisability of Optical Flow Models](https://mlsanity.com/paper/2607.10470/) (2026)
- [Learning Semantic-Robust Change Detection via Semantic-Invariant Self-Distillation](https://mlsanity.com/paper/2607.19000/) (2026)
- [FAST: Flow Any Scene Transformer](https://mlsanity.com/paper/2609.39748/) (2026)

## Abstract (arXiv)

Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied to real-world applications and limits the benefits of scaling up datasets. To address these challenges, we propose Flow-Anything, a large-scale data generation framework designed to learn optical flow estimation from any single-view images in the real world. We employ two effective steps to make data scaling-up promising. First, we convert a single-view image into a 3D representation using advanced monocular depth estimation networks. This allows us to render optical flow and novel view images under a virtual camera. Second, we develop an Object-Independent Volume Rendering module and a Depth-Aware Inpainting module to model the dynamic objects in the 3D representation. These two steps allow us to generate realistic datasets for training from large-scale single-view images, namely FA-Flow Dataset. For the first time, we demonstrate the benefits of generating optical flow training data from large-scale real-world images, outperforming the most advanced unsupervised methods and supervised methods on synthetic datasets. Moreover, our models serve as a foundation model and enhance the performance of various downstream video tasks.