# DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework

arXiv: https://arxiv.org/abs/2503.14880 · HTML: https://mlsanity.com/paper/2503.14880/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 72 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Builds on (most cited first, 30 of 46)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [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)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (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)
- [Kubric: A scalable dataset generator](https://mlsanity.com/paper/2203.03570/) (2022)
- [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)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [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)
- [Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo](https://mlsanity.com/paper/2303.01943/) (2023)
- [Playing for Benchmarks](https://mlsanity.com/paper/1709.07322/) (2017)
- [CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow](https://mlsanity.com/paper/2211.10408/) (2022)
- [Delving Deeper into Convolutional Networks for Learning Video Representations](https://mlsanity.com/paper/1511.06432/) (2015)
- [Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation](https://mlsanity.com/paper/1904.05290/) (2019)
- [The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation](https://mlsanity.com/paper/2306.01923/) (2023)
- [FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation](https://mlsanity.com/paper/2303.01237/) (2023)

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

- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling](https://mlsanity.com/paper/2509.12201/) (2025)
- [Puppeteer: Rig and Animate Your 3D Models](https://mlsanity.com/paper/2508.10898/) (2025)
- [WAFT: Warping-Alone Field Transforms for Optical Flow](https://mlsanity.com/paper/2506.21526/) (2025)
- [MegaFlow: Zero-Shot Large Displacement Optical Flow](https://mlsanity.com/paper/2603.25739/) (2026)
- [Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals](https://mlsanity.com/paper/2503.19953/) (2025)
- [Learning Efficient Meshflow and Optical Flow from Event Cameras](https://mlsanity.com/paper/2510.04111/) (2025)
- [WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching](https://mlsanity.com/paper/2603.24836/) (2026)
- [CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration](https://mlsanity.com/paper/2604.05689/) (2026)
- [Human detectors are surprisingly powerful reward models](https://mlsanity.com/paper/2601.14037/) (2026)
- [Zero-shot World Models Are Developmentally Efficient Learners](https://mlsanity.com/paper/2604.10333/) (2026)
- [Why Latent Actions Fail, and How to Prevent It](https://mlsanity.com/paper/2605.20223/) (2026)
- [Unified 3D Scene Understanding Through Physical World Modeling](https://mlsanity.com/paper/2605.24321/) (2026)
- [Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation](https://mlsanity.com/paper/2505.16942/) (2025)
- [CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion](https://mlsanity.com/paper/2510.12362/) (2025)
- [Towards Reliable Sea Ice Drift Estimation in the Arctic Deep Learning Optical Flow on RADARSAT-2](https://mlsanity.com/paper/2510.26653/) (2025)
- [A Study of Finetuning Video Transformers for Multi-view Geometry Tasks](https://mlsanity.com/paper/2512.18684/) (2025)
- [DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesis](https://mlsanity.com/paper/2602.23022/) (2026)
- [Unsupervised Real-World Super-Resolution via Rectified Flow Degradation Modelling](https://mlsanity.com/paper/2508.07214/) (2025)
- [GeoDiffMM: Geometry-Guided Conditional Diffusion for Motion Magnification](https://mlsanity.com/paper/2512.08325/) (2025)
- [SRFlow: A Dataset and Regularization Model for High-Resolution Facial Optical Flow via Splatting Rasterization](https://mlsanity.com/paper/2601.06479/) (2026)
- [GVGS: Gaussian Visibility-Aware Multi-View Geometry for Accurate Surface Reconstruction](https://mlsanity.com/paper/2601.20331/) (2026)
- [FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow](https://mlsanity.com/paper/2603.28759/) (2026)
- [Motion-guided sparse correction enables expert-quality point tracking across diverse microscopy regimes](https://mlsanity.com/paper/2605.29220/) (2026)
- [Perceptual 3D Simulation With Physical World Modeling](https://mlsanity.com/paper/2606.27575/) (2026)
- [RBE-Flow: Recurrent Bayesian Estimation on Feature Manifolds for Cross-Modal Registration](https://mlsanity.com/paper/2606.30492/) (2026)
- [FlowPainter: Inpainting Optical Flow via Confidence-Guided Completion](https://mlsanity.com/paper/2607.10140/) (2026)
- [WiFlow: Estimating Optical Flow using WiFi Channel State Information](https://mlsanity.com/paper/2609.02452/) (2026)
- [FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation](https://mlsanity.com/paper/2609.11486/) (2026)
- [E-WAVE: Event-based Continuous Optical Flow via Warping-Aligned Visual Encoding](https://mlsanity.com/paper/2609.34346/) (2026)

## Abstract (arXiv)

Optical flow estimation is essential for video processing tasks, such as restoration and action recognition. The quality of videos is constantly increasing, with current standards reaching 8K resolution. However, optical flow methods are usually designed for low resolution and do not generalize to large inputs due to their rigid architectures. They adopt downscaling or input tiling to reduce the input size, causing a loss of details and global information. There is also a lack of optical flow benchmarks to judge the actual performance of existing methods on high-resolution samples. Previous works only conducted qualitative high-resolution evaluations on hand-picked samples. This paper fills this gap in optical flow estimation in two ways. We propose DPFlow, an adaptive optical flow architecture capable of generalizing up to 8K resolution inputs while trained with only low-resolution samples. We also introduce Kubric-NK, a new benchmark for evaluating optical flow methods with input resolutions ranging from 1K to 8K. Our high-resolution evaluation pushes the boundaries of existing methods and reveals new insights about their generalization capabilities. Extensive experimental results show that DPFlow achieves state-of-the-art results on the MPI-Sintel, KITTI 2015, Spring, and other high-resolution benchmarks.