# Warp Consistency for Unsupervised Learning of Dense Correspondences

arXiv: https://arxiv.org/abs/2104.03308 · HTML: https://mlsanity.com/paper/2104.03308/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 85 references that are in the map.
- First posted on arXiv 7 Apr 2021.

## Builds on (most cited first, 30 of 55)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [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)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [Learning Correspondence from the Cycle-Consistency of Time](https://mlsanity.com/paper/1903.07593/) (2019)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [Space-Time Correspondence as a Contrastive Random Walk](https://mlsanity.com/paper/2006.14613/) (2020)
- [UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss](https://mlsanity.com/paper/1711.07837/) (2017)
- [Neighbourhood Consensus Networks](https://mlsanity.com/paper/1810.10510/) (2018)
- [DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks](https://mlsanity.com/paper/1704.02470/) (2017)
- [Temporal Cycle-Consistency Learning](https://mlsanity.com/paper/1904.07846/) (2019)
- [Learning Two-View Correspondences and Geometry Using Order-Aware Network](https://mlsanity.com/paper/1908.04964/) (2019)
- [SPair-71k: A Large-scale Benchmark for Semantic Correspondence](https://mlsanity.com/paper/1908.10543/) (2019)
- [GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences](https://mlsanity.com/paper/1912.05524/) (2019)
- [Convolutional neural network architecture for geometric matching](https://mlsanity.com/paper/1703.05593/) (2017)
- [SelFlow: Self-Supervised Learning of Optical Flow](https://mlsanity.com/paper/1904.09117/) (2019)
- [Visual Attribute Transfer through Deep Image Analogy](https://mlsanity.com/paper/1705.01088/) (2017)
- [Return of the Devil in the Details: Delving Deep into Convolutional Nets](https://mlsanity.com/paper/1405.3531/) (2014)
- [Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation](https://mlsanity.com/paper/2003.13045/) (2020)

## Built on by (most cited first, 30 of 42)

- [Emergent Correspondence from Image Diffusion](https://mlsanity.com/paper/2306.03881/) (2023)
- [A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence](https://mlsanity.com/paper/2305.15347/) (2023)
- [Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence](https://mlsanity.com/paper/2311.17034/) (2023)
- [DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization](https://mlsanity.com/paper/2402.09812/) (2024)
- [DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector](https://mlsanity.com/paper/2404.08928/) (2024)
- [Learning Pixel Trajectories with Multiscale Contrastive Random Walks](https://mlsanity.com/paper/2201.08379/) (2022)
- [Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions](https://mlsanity.com/paper/2207.06825/) (2022)
- [One-Shot Transfer of Affordance Regions? AffCorrs!](https://mlsanity.com/paper/2209.07147/) (2022)
- [Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences](https://mlsanity.com/paper/2203.04279/) (2022)
- [A case for using rotation invariant features in state of the art feature matchers](https://mlsanity.com/paper/2204.10144/) (2022)
- [ASIC: Aligning Sparse in-the-wild Image Collections](https://mlsanity.com/paper/2303.16201/) (2023)
- [Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild](https://mlsanity.com/paper/2210.07199/) (2022)
- [Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection](https://mlsanity.com/paper/2311.11273/) (2023)
- [Learning Co-segmentation by Segment Swapping for Retrieval and Discovery](https://mlsanity.com/paper/2110.15904/) (2021)
- [Towards Training-free Open-world Segmentation via Image Prompt Foundation Models](https://mlsanity.com/paper/2310.10912/) (2023)
- [Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels](https://mlsanity.com/paper/2506.05312/) (2025)
- [SHIC: Shape-Image Correspondences with no Keypoint Supervision](https://mlsanity.com/paper/2407.18907/) (2024)
- [Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint](https://mlsanity.com/paper/2212.02763/) (2022)
- [GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning](https://mlsanity.com/paper/2301.10018/) (2023)
- [Zero-Shot Image Feature Consensus with Deep Functional Maps](https://mlsanity.com/paper/2403.12038/) (2024)
- [Consistent Image Layout Editing with Diffusion Models](https://mlsanity.com/paper/2503.06419/) (2025)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [Doduo: Learning Dense Visual Correspondence from Unsupervised Semantic-Aware Flow](https://mlsanity.com/paper/2309.15110/) (2023)
- [Warping the Residuals for Image Editing with StyleGAN](https://mlsanity.com/paper/2312.11422/) (2023)
- [Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence](https://mlsanity.com/paper/2506.08220/) (2025)
- [Towards Content-based Pixel Retrieval in Revisited Oxford and Paris](https://mlsanity.com/paper/2309.05438/) (2023)
- [Zero-Shot Co-salient Object Detection Framework](https://mlsanity.com/paper/2309.05499/) (2023)
- [CONDA: Condensed Deep Association Learning for Co-Salient Object Detection](https://mlsanity.com/paper/2409.01021/) (2024)
- [SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models](https://mlsanity.com/paper/2503.14129/) (2025)
- [Semantic Correspondence: Unified Benchmarking and a Strong Baseline](https://mlsanity.com/paper/2505.18060/) (2025)

## Abstract (arXiv)

The key challenge in learning dense correspondences lies in the lack of ground-truth matches for real image pairs. While photometric consistency losses provide unsupervised alternatives, they struggle with large appearance changes, which are ubiquitous in geometric and semantic matching tasks. Moreover, methods relying on synthetic training pairs often suffer from poor generalisation to real data. We propose Warp Consistency, an unsupervised learning objective for dense correspondence regression. Our objective is effective even in settings with large appearance and view-point changes. Given a pair of real images, we first construct an image triplet by applying a randomly sampled warp to one of the original images. We derive and analyze all flow-consistency constraints arising between the triplet. From our observations and empirical results, we design a general unsupervised objective employing two of the derived constraints. We validate our warp consistency loss by training three recent dense correspondence networks for the geometric and semantic matching tasks. Our approach sets a new state-of-the-art on several challenging benchmarks, including MegaDepth, RobotCar and TSS. Code and models are at github.com/PruneTruong/DenseMatching.