# MambaFlow: A Mamba-Centric Architecture for End-to-End Optical Flow Estimation

arXiv: https://arxiv.org/abs/2503.07046 · HTML: https://mlsanity.com/paper/2503.07046/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 50 of its 69 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Vision Mamba backbones](https://mlsanity.com/ssm/vision-mamba-backbones/)

## Builds on (most cited first, 30 of 50)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers](https://mlsanity.com/paper/2110.13985/) (2021)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Optical Flow Estimation using a Spatial Pyramid Network](https://mlsanity.com/paper/1611.00850/) (2016)
- [U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation](https://mlsanity.com/paper/2401.04722/) (2024)
- [YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark](https://mlsanity.com/paper/1809.03327/) (2018)
- [VideoMamba: State Space Model for Efficient Video Understanding](https://mlsanity.com/paper/2403.06977/) (2024)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [FlowFormer: A Transformer Architecture for Optical Flow](https://mlsanity.com/paper/2203.16194/) (2022)
- [SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation](https://mlsanity.com/paper/2401.13560/) (2024)
- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [Real-Time Intermediate Flow Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2011.06294/) (2020)
- [Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining](https://mlsanity.com/paper/2402.03302/) (2024)
- [SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow](https://mlsanity.com/paper/2405.14793/) (2024)
- [Playing for Benchmarks](https://mlsanity.com/paper/1709.07322/) (2017)
- [Quadratic video interpolation](https://mlsanity.com/paper/1911.00627/) (2019)
- [MambaOut: Do We Really Need Mamba for Vision?](https://mlsanity.com/paper/2405.07992/) (2024)
- [FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation](https://mlsanity.com/paper/2303.01237/) (2023)
- [Selective Structured State-Spaces for Long-Form Video Understanding](https://mlsanity.com/paper/2303.14526/) (2023)
- [The Hidden Attention of Mamba Models](https://mlsanity.com/paper/2403.01590/) (2024)
- [MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathology](https://mlsanity.com/paper/2403.06800/) (2024)
- [ZigMa: A DiT-style Zigzag Mamba Diffusion Model](https://mlsanity.com/paper/2403.13802/) (2024)
- [CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow](https://mlsanity.com/paper/2203.16896/) (2022)
- [Global Matching with Overlapping Attention for Optical Flow Estimation](https://mlsanity.com/paper/2203.11335/) (2022)

## Built on by (most cited first, 2 of 2)

- [MTIL: Encoding Full History with Mamba for Temporal Imitation Learning](https://mlsanity.com/paper/2505.12410/) (2025)
- [AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation](https://mlsanity.com/paper/2506.01061/) (2025)

## Abstract (arXiv)

Recently, the Mamba architecture has demonstrated significant successes in various computer vision tasks, such as classification and segmentation. However, its application to optical flow estimation remains unexplored. In this paper, we introduce MambaFlow, a novel framework designed to leverage the high accuracy and efficiency of the Mamba architecture for capturing locally correlated features while preserving global information in end-to-end optical flow estimation. To our knowledge, MambaFlow is the first architecture centered around the Mamba design tailored specifically for optical flow estimation. It comprises two key components: (1) PolyMamba, which enhances feature representation through a dual-Mamba architecture, incorporating a Self-Mamba module for intra-token modeling and a Cross-Mamba module for inter-modality interaction, enabling both deep contextualization and effective feature fusion; and (2) PulseMamba, which leverages an Attention Guidance Aggregator (AGA) to adaptively integrate features with dynamically learned weights in contrast to naive concatenation, and then employs the intrinsic recurrent mechanism of Mamba to perform autoregressive flow decoding, facilitating efficient flow information dissemination. Extensive experiments demonstrate that MambaFlow achieves remarkable results comparable to mainstream methods on benchmark datasets. Compared to SEA-RAFT, MambaFlow attains higher accuracy on the Sintel benchmark, demonstrating stronger potential for real-world deployment on resource-constrained devices. The source code will be made publicly available upon acceptance of the paper.