# LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation

arXiv: https://arxiv.org/abs/2007.09319 · HTML: https://mlsanity.com/paper/2007.09319/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2020.

## Built on by (most cited first, 30 of 37)

- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [CelebV-HQ: A Large-Scale Video Facial Attributes Dataset](https://mlsanity.com/paper/2207.12393/) (2022)
- [CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow](https://mlsanity.com/paper/2203.16896/) (2022)
- [DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow](https://mlsanity.com/paper/2204.00330/) (2022)
- [TMA: Temporal Motion Aggregation for Event-based Optical Flow](https://mlsanity.com/paper/2303.11629/) (2023)
- [Learning optical flow from still images](https://mlsanity.com/paper/2104.03965/) (2021)
- [SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation](https://mlsanity.com/paper/2105.04447/) (2021)
- [RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes](https://mlsanity.com/paper/2303.04456/) (2023)
- [CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Driving](https://mlsanity.com/paper/2202.00909/) (2022)
- [NanoFlowNet: Real-time Dense Optical Flow on a Nano Quadcopter](https://mlsanity.com/paper/2209.06918/) (2022)
- [FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases](https://mlsanity.com/paper/2509.05297/) (2025)
- [ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Sampling](https://mlsanity.com/paper/2104.03560/) (2021)
- [Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining](https://mlsanity.com/paper/2505.16811/) (2025)
- [NeuFlow: Real-time, High-accuracy Optical Flow Estimation on Robots Using Edge Devices](https://mlsanity.com/paper/2403.10425/) (2024)
- [NeuFlow v2: Push High-Efficiency Optical Flow To the Limit](https://mlsanity.com/paper/2408.10161/) (2024)
- [DDCNet: Deep Dilated Convolutional Neural Network for Dense Prediction](https://mlsanity.com/paper/2107.04715/) (2021)
- [Detail Preserving Residual Feature Pyramid Modules for Optical Flow](https://mlsanity.com/paper/2107.10990/) (2021)
- [Sensor-Guided Optical Flow](https://mlsanity.com/paper/2109.15321/) (2021)
- [Learning Fine-Grained Features for Pixel-wise Video Correspondences](https://mlsanity.com/paper/2308.03040/) (2023)
- [DCVNet: Dilated Cost Volume Networks for Fast Optical Flow](https://mlsanity.com/paper/2103.17271/) (2021)
- [Learning Scene Flow in 3D Point Clouds with Noisy Pseudo Labels](https://mlsanity.com/paper/2203.12655/) (2022)
- [Unsupervised Flow Refinement near Motion Boundaries](https://mlsanity.com/paper/2208.02305/) (2022)
- [Attentive Multimodal Fusion for Optical and Scene Flow](https://mlsanity.com/paper/2307.15301/) (2023)
- [SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations](https://mlsanity.com/paper/2404.08135/) (2024)
- [Improving Optical Flow and Stereo Depth Estimation by Leveraging Uncertainty-Based Learning Difficulties](https://mlsanity.com/paper/2506.00324/) (2025)
- [Channel-wise Motion Features for Efficient Motion Segmentation](https://mlsanity.com/paper/2507.13082/) (2025)
- [DDCNet-Multires: Effective Receptive Field Guided Multiresolution CNN for Dense Prediction](https://mlsanity.com/paper/2107.05634/) (2021)
- [INV-Flow2PoseNet: Light-Resistant Rigid Object Pose from Optical Flow of RGB-D Images using Images, Normals and Vertices](https://mlsanity.com/paper/2209.06562/) (2022)
- [CGCV:Context Guided Correlation Volume for Optical Flow Neural Networks](https://mlsanity.com/paper/2212.10174/) (2022)

## Abstract (arXiv)

Deep learning approaches have achieved great success in addressing the problem of optical flow estimation. The keys to success lie in the use of cost volume and coarse-to-fine flow inference. However, the matching problem becomes ill-posed when partially occluded or homogeneous regions exist in images. This causes a cost volume to contain outliers and affects the flow decoding from it. Besides, the coarse-to-fine flow inference demands an accurate flow initialization. Ambiguous correspondence yields erroneous flow fields and affects the flow inferences in subsequent levels. In this paper, we introduce LiteFlowNet3, a deep network consisting of two specialized modules, to address the above challenges. (1) We ameliorate the issue of outliers in the cost volume by amending each cost vector through an adaptive modulation prior to the flow decoding. (2) We further improve the flow accuracy by exploring local flow consistency. To this end, each inaccurate optical flow is replaced with an accurate one from a nearby position through a novel warping of the flow field. LiteFlowNet3 not only achieves promising results on public benchmarks but also has a small model size and a fast runtime.