# Learning Accurate Dense Correspondences and When to Trust Them

arXiv: https://arxiv.org/abs/2101.01710 · HTML: https://mlsanity.com/paper/2101.01710/

## Key facts

- Cited by 113 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 80 references that are in the map.
- First posted on arXiv 5 Jan 2021.

## Builds on (most cited first, 30 of 47)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [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)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [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)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [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)
- [Meta-learning with differentiable closed-form solvers](https://mlsanity.com/paper/1805.08136/) (2018)
- [YFCC100M: The New Data in Multimedia Research](https://mlsanity.com/paper/1503.01817/) (2015)
- [Probabilistic Regression for Visual Tracking](https://mlsanity.com/paper/2003.12565/) (2020)
- [R2D2: Repeatable and Reliable Detector and Descriptor](https://mlsanity.com/paper/1906.06195/) (2019)
- [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)
- [Learning Two-View Correspondences and Geometry Using Order-Aware Network](https://mlsanity.com/paper/1908.04964/) (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)
- [Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow](https://mlsanity.com/paper/1802.07095/) (2018)
- [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)
- [Hierarchical Discrete Distribution Decomposition for Match Density Estimation](https://mlsanity.com/paper/1812.06264/) (2018)
- [Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions](https://mlsanity.com/paper/2004.10566/) (2020)
- [Handheld Multi-Frame Super-Resolution](https://mlsanity.com/paper/1905.03277/) (2019)
- [EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow](https://mlsanity.com/paper/1501.02565/) (2015)

## Built on by (most cited first, 30 of 113)

- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence](https://mlsanity.com/paper/2305.15347/) (2023)
- [Pixel-Perfect Structure-from-Motion with Featuremetric Refinement](https://mlsanity.com/paper/2108.08291/) (2021)
- [SPARF: Neural Radiance Fields from Sparse and Noisy Poses](https://mlsanity.com/paper/2211.11738/) (2022)
- [Tracking Everything Everywhere All at Once](https://mlsanity.com/paper/2306.05422/) (2023)
- [Deep Patch Visual Odometry](https://mlsanity.com/paper/2208.04726/) (2022)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer](https://mlsanity.com/paper/2208.14201/) (2022)
- [Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed](https://mlsanity.com/paper/2403.04765/) (2024)
- [Towards Grand Unification of Object Tracking](https://mlsanity.com/paper/2207.07078/) (2022)
- [NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields](https://mlsanity.com/paper/2203.01913/) (2022)
- [Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence](https://mlsanity.com/paper/2311.17034/) (2023)
- [PDC-Net+: Enhanced Probabilistic Dense Correspondence Network](https://mlsanity.com/paper/2109.13912/) (2021)
- [Local All-Pair Correspondence for Point Tracking](https://mlsanity.com/paper/2407.15420/) (2024)
- [CATs: Cost Aggregation Transformers for Visual Correspondence](https://mlsanity.com/paper/2106.02520/) (2021)
- [Detector-Free Structure from Motion](https://mlsanity.com/paper/2306.15669/) (2023)
- [GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://mlsanity.com/paper/2304.02008/) (2023)
- [OmniGlue: Generalizable Feature Matching with Foundation Model Guidance](https://mlsanity.com/paper/2405.12979/) (2024)
- [CATs++: Boosting Cost Aggregation with Convolutions and Transformers](https://mlsanity.com/paper/2202.06817/) (2022)
- [DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation](https://mlsanity.com/paper/2305.14330/) (2023)
- [Dens3R: A Foundation Model for 3D Geometry Prediction](https://mlsanity.com/paper/2507.16290/) (2025)
- [MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training](https://mlsanity.com/paper/2501.07556/) (2025)
- [MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2302.08788/) (2023)
- [UFM: A Simple Path towards Unified Dense Correspondence with Flow](https://mlsanity.com/paper/2506.09278/) (2025)
- [Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report](https://mlsanity.com/paper/2105.07809/) (2021)
- [Reconstructing People, Places, and Cameras](https://mlsanity.com/paper/2412.17806/) (2024)
- [Emergent Temporal Correspondences from Video Diffusion Transformers](https://mlsanity.com/paper/2506.17220/) (2025)
- [Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences](https://mlsanity.com/paper/2203.04279/) (2022)

## Abstract (arXiv)

Establishing dense correspondences between a pair of images is an important and general problem. However, dense flow estimation is often inaccurate in the case of large displacements or homogeneous regions. For most applications and down-stream tasks, such as pose estimation, image manipulation, or 3D reconstruction, it is crucial to know when and where to trust the estimated matches. In this work, we aim to estimate a dense flow field relating two images, coupled with a robust pixel-wise confidence map indicating the reliability and accuracy of the prediction. We develop a flexible probabilistic approach that jointly learns the flow prediction and its uncertainty. In particular, we parametrize the predictive distribution as a constrained mixture model, ensuring better modelling of both accurate flow predictions and outliers. Moreover, we develop an architecture and training strategy tailored for robust and generalizable uncertainty prediction in the context of self-supervised training. Our approach obtains state-of-the-art results on multiple challenging geometric matching and optical flow datasets. We further validate the usefulness of our probabilistic confidence estimation for the task of pose estimation. Code and models are available at https://github.com/PruneTruong/PDCNet.