Semantic Correspondence Methods Paper List

October 8, 2025 · View on GitHub

🏠 About

To provide a structured understanding of semantic correspondence methods, we present a taxonomy categorizing approaches into handcrafted descriptors, architectural improvements, and training strategy improvements. This taxonomy traces the evolution from handcrafted methods to advanced deep learning solutions, providing a clear overview of how different approaches enhance feature quality, matching performance, and training strategies. alt text

Handcrafted Descriptors

A Maximum Entropy Framework for Part-Based Texture and Object Recognition
Svetlana Lazebnik, Cordelia Schmid, Jean Ponce
ICCV 2005. [Paper]
Flexible Object Models for Category-Level 3D Object Recognition
Akash Kushal, Cordelia Schmid, Jean Ponce
CVPR 2007. [Paper]
Sift Flow: Dense Correspondence Across Scenes and Its Applications
Ce Liu, Jenny Yuen, Antonio Torralba
TPAMI 2011. [Paper] [Code]
Deformable Spatial Pyramid Matching for Fast Dense Correspondences
Jaechul Kim, Ce Liu, Fei Sha, Kristen Grauman
CVPR 2013. [Paper]
DAISY Filter Flow: A Generalized Discrete Approach to Dense Correspondences
Hongsheng Yang, Wen-Yan Lin, Jiangbo Lu
CVPR 2014. [Paper] [Code]
Unsupervised Object Discovery and Localization in the Wild: Part-Based Matching with Bottom-Up Region Proposals
Minsu Cho, Suha Kwak, Cordelia Schmid, Jean Ponce
CVPR 2015. [Paper]
Proposal Flow
Bumsub Ham, Minsu Cho, Cordelia Schmid, Jean Ponce
CVPR 2016. [Paper] [Project Page] [Code]
Proposal Flow: Semantic Correspondences from Object Proposals
Bumsub Ham, Minsu Cho, Cordelia Schmid, Jean Ponce
TPAMI 2018. [Paper] [Project Page] [Code]
Flexible Object Models for Category-Level 3D Object Recognition
Akash Kushal, Cordelia Schmid, Jean Ponce
CVPR 2007. [Paper]
Sift Flow: Dense Correspondence Across Scenes and Its Applications
Ce Liu, Jenny Yuen, Antonio Torralba
TPAMI 2011. [Paper] [Code]
Deformable Spatial Pyramid Matching for Fast Dense Correspondences
Jaechul Kim, Ce Liu, Fei Sha, Kristen Grauman
CVPR 2013. [Paper]
DAISY Filter Flow: A Generalized Discrete Approach to Dense Correspondences
Hongsheng Yang, Wen-Yan Lin, Jiangbo Lu
CVPR 2014. [Paper] [Code]
Unsupervised Object Discovery and Localization in the Wild: Part-Based Matching with Bottom-Up Region Proposals
Minsu Cho, Suha Kwak, Cordelia Schmid, Jean Ponce
CVPR 2015. [Paper]
Proposal Flow
Bumsub Ham, Minsu Cho, Cordelia Schmid, Jean Ponce
CVPR 2016. [Paper] [Project Page] [Code]
Proposal Flow: Semantic Correspondences from Object Proposals
Bumsub Ham, Minsu Cho, Cordelia Schmid, Jean Ponce
TPAMI 2018. [Paper] [Project Page] [Code]

Architectural Improvement

Early CNN methods

Universal Correspondence Network
Christopher B. Choy, JunYoung Gwak, Silvio Savarese, Manmohan Chandraker
NeurIPS 2016. [Paper] [Code]
SCNet: Learning Semantic Correspondence
Kai Han, Rafael S. Rezende, Bumsub Ham, Kwan-Yee K. Wong, Minsu Cho, Cordelia Schmid, Jean Ponce
ICCV 2017. [Paper] [Project Page] [Code]
FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence
Seungryong Kim, Dongbo Min, Bumsub Ham, Stephen Lin, Kwanghoon Sohn
CVPR 2017. [Paper] TPAMI 2019. [Paper] [Project Page] [Code]

Feature Enhancement

Feature Assembly

Hypercolumns for Object Segmentation and Fine-grained Localization
Bharath Hariharan, Pablo Arbeláez, Ross Girshick, Jitendra Malik
CVPR 2015. [Paper]
Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features
Juhong Min, Jongmin Lee, Jean Ponce, Minsu Cho
ICCV 2019. [Paper] [Project Page] [Code]
Learning to Compose Hypercolumns for Visual Correspondence
Juhong Min, Jongmin Lee, Jean Ponce, Minsu Cho
ECCV 2020. [Paper] [Project Page] [Code]
Multi-scale Matching Networks for Semantic Correspondence Dongyang Zhao, Ziyang Song, Zhenghao Ji, Gangming Zhao, Weifeng Ge, Yizhou Yu ICCV 2021. [Paper] [Code]
Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence
Grace Luo, Lisa Dunlap, Dong Huk Park, Aleksander Holynski, Trevor Darrell
NeurIPS 2023. [Paper] [Project Page] [Code]
A Tale of Two Features: Stable Diffusion Complements Dino for Zero-shot Semantic Correspondence
Junyi Zhang, Charles Herrmann, Junhwa Hur, Luisa Polania Cabrera, Varun Jampani, Deqing Sun, Ming-Hsuan Yang
NeurIPS 2023. [Paper] [Project Page] [Code]
Efficient Semantic Matching with Hypercolumn Correlation
Seungwook Kim, Juhong Min, Minsu Cho
WACV 2024. [Paper] [Project Page] [Code]
Independently Keypoint Learning for Small Object Semantic Correspondence
Hailong Jin, Huiying Li
arXiv preprint 2024. [Paper]
Pixel-level Semantic Correspondence through Layout-aware Representation Learning and Multi-scale Matching Integration
Yixuan Sun, Zhangyue Yin, Haibo Wang, Yan Wang, Xipeng Qiu, Weifeng Ge
CVPR 2024. [Paper] [Code]

Feature Adaptation

SimSC: A Simple Framework for Semantic Correspondence with Temperature Learning
Xinghui Li, Kai Han, Xingchen Wan, Victor Adrian Prisacariu
arXiv preprint 2023. [Paper]
Unsupervised Semantic Correspondence Using Stable Diffusion
Eric Hedlin, Gopal Sharma, Shweta Mahajan, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, Kwang Moo Yi
NeurIPS 2023. [Paper] [Project Page] [Code]
SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matching
Xinghui Li, Jingyi Lu, Kai Han, Victor Adrian Prisacariu
CVPR 2024. [Paper]
[Project Page] [Code]
Telling Left from Right: Identifying Geometry-aware Semantic Correspondence
Junyi Zhang, Charles Herrmann, Junhwa Hur, Eric Chen, Varun Jampani, Deqing Sun, Ming-Hsuan Yang
CVPR 2024. [Paper] [Project Page] [Code]
LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors
Saksham Suri, Matthew Walmer, Kamal Gupta, Abhinav Shrivastava
ECCV 2024. [Paper] [Project Page] [Code]
CleanDIFT: Diffusion Features without Noise
Nick Stracke, Stefan Andreas Baumann, Kolja Bauer, Frank Fundel, Björn Ommer
CVPR 2025 Oral. [Paper] [Project Page] [Code]
SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representations
Krispin Wandel, Hesheng Wang
CVPR 2025. [Paper] [Project Page] [Code]
Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations
Chaofan Gan, Yuanpeng Tu, Xi Chen, Tieyuan Chen, Yuxi Li, Mehrtash Harandi, Weiyao Lin
arXiv preprint 2025. [Paper]

Cost Volume-Based Methods

Neighbourhood Consensus Networks
Ignacio Rocco, Mircea Cimpoi, Relja Arandjelović, Akihiko Torii, Tomas Pajdla, Josef Sivic
NeurIPS 2018. [Paper] [Project Page] [Code]
Correspondence Networks with Adaptive Neighbourhood Consensus
Shuda Li, Kai Han, Theo W. Costain, Henry Howard-Jenkins, Victor Adrian Prisacariu
CVPR 2020. [Paper] [Project Page] [Code]
Dual-resolution Correspondence Networks
Xinghui Li, Kai Han, Shuda Li, Victor Adrian Prisacariu
NeurIPS 2020. [Paper] [Project Page] [Code]
Convolutional Hough Matching Networks
Juhong Min, Minsu Cho
CVPR 2021. [Paper] [Code]
Patchmatch-based Neighbourhood Consensus for Semantic Correspondence
Jae Yong Lee, Joseph DeGol, Victor Fragoso, Sudipta N. Sinha
CVPR 2021. [Paper] [Code]
Cats: Cost Aggregation Transformers for Visual Correspondence
Seokju Cho, Sunghwan Hong, Sangryul Jeon, Yunsung Lee, Kwanghoon Sohn, Seungryong Kim
NeurIPS 2021. [Paper] [Code]
Cost Aggregation with 4D Convolutional Swin Transformer for Few-shot Segmentation
Sunghwan Hong, Seokju Cho, Jisu Nam, Stephen Lin, Seungryong Kim
ECCV 2022. [Paper] [Project Page] [Code]
Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
Sunghwan Hong, Jisu Nam, Seokju Cho, Susung Hong, Sangryul Jeon, Dongbo Min, Seungryong Kim
NeurIPS 2022. [Paper] [Project Page] [Code]
Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence
Sunghwan Hong, Seokju Cho, Seungryong Kim, Stephen Lin
arXiv preprint 2022. [Paper]
Transformatcher: Match-to-Match Attention for Semantic Correspondence
Seungwook Kim, Juhong Min, Minsu Cho
CVPR 2022. [Paper] [Project Page] [Code]
Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence
Juhong Min, Seungwook Kim, Minsu Cho
TPAMI 2023. [Paper] [Code]
Cats++: Boosting Cost Aggregation with Convolutions and Transformers
Seokju Cho, Sunghwan Hong, Seungryong Kim
TPAMI 2023. [Paper] [Project Page] [Code]
Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence
Sunghwan Hong, Seokju Cho, Seungryong Kim, Stephen Lin
ICLR 2024. [Paper]
DualRC: A Dual-Resolution Learning Framework With Neighbourhood Consensus for Visual Correspondences
Xinghui Li, Kai Han, Shuda Li, Victor Adrian Prisacariu
TPAMI 2024. [Paper] [Project Page] [Code]

Flow Field-Based Methods

SFNet: Learning Object-aware Semantic Correspondence
Junghyup Lee, Dohyung Kim, Jean Ponce, Bumsub Ham
CVPR 2019. [Paper] [Project Page] [Code]
GLU-Net: Global-local Universal Network for Dense Flow and Correspondences
Prune Truong, Martin Danelljan, Radu Timofte
CVPR 2020 Oral. [Paper] [Code]
Learning Semantic Correspondence Exploiting an Object-level Prior
Junghyup Lee, Dohyung Kim, Wonkyung Lee, Jean Ponce, Bumsub Ham
TPAMI 2022. [Paper]
Correspondence Transformers with Asymmetric Feature Learning and Matching Flow Super-Resolution
Yixuan Sun, Dongyang Zhao, Zhangyue Yin, Yiwen Huang, Tao Gui, Wenqiang Zhang
CVPR 2023. [Paper] [Code]
Pixel-Level Semantic Correspondence through Layout-Aware Representation Learning and Multi-Scale Matching Integration
Yixuan Sun, Zhangyue Yin, Haibo Wang, Yan Wang, Xipeng Qiu, Weifeng Ge
CVPR 2024. [Paper] [Code]

Parameterized Transformation-Based Methods

Attentive Semantic Alignment with Offset-Aware Correlation Kernels
Paul Hongsuck Seo, Jongmin Lee, Deunsol Jung, Bohyung Han, Minsu Cho
ECCV 2018. [Paper]
End-to-End Weakly-Supervised Semantic Alignment
Ignacio Rocco, Relja Arandjelović, Josef Sivic
CVPR 2018. [Paper] [Code]
Recurrent Transformer Networks for Semantic Correspondence
Seungryong Kim, Stephen Lin, Sangryul Jeon, Dongbo Min, Kwanghoon Sohn
NeurIPS 2018. [Paper] [Project Page] [Code]
PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence
Sangryul Jeon, Seungryong Kim, Dongbo Min, Kwanghoon Sohn
ECCV 2018. [Paper]

Other Improvements

Space-Time Correspondence as a Contrastive Random Walk
Allan Jabri, Andrew Owens, Alexei A. Efros
NeurIPS 2021. [Paper] [Project Page] [Code]
Deep Matching Prior: Test-Time Optimization for Dense Correspondence
Sunghwan Hong, Seungryong Kim
ICCV 2021. [Paper]
Deep ViT Features as Dense Visual Descriptors
Shir Amir, Yossi Gandelsman, Shai Bagon, Tali Dekel
ECCVW 2022. [Paper] [Project Page] [Code]
GAN-Supervised Dense Visual Alignment
William Peebles, Jun-Yan Zhu, Richard Zhang, Antonio Torralba, Alexei A. Efros, Eli Shechtman
CVPR 2022 Oral. [Paper] [Code]
CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs
Jiteng Mu, Shalini De Mello, Zhiding Yu, Nuno Vasconcelos, Xiaolong Wang, Jan Kautz, Sifei Liu
CVPR 2022. [Paper] [Project Page] [Code]
Zero-Shot Image Feature Consensus with Deep Functional Maps
Xinle Cheng, Congyue Deng, Adam Harley, Yixin Zhu, Leonidas Guibas
ECCV 2024. [Paper] [Code]

Training Strategy Improvement

Non-Keypoint Label-Based Methods

Proposal Flow
Bumsub Ham, Minsu Cho, Cordelia Schmid, Jean Ponce
CVPR 2016. [Paper] [Project Page] [Code]
Proposal Flow: Semantic Correspondences from Object Proposals
Bumsub Ham, Minsu Cho, Cordelia Schmid, Jean Ponce
TPAMI 2018. [Paper] [Project Page] [Code]
FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence
Seungryong Kim, Dongbo Min, Bumsub Ham, Stephen Lin, Kwanghoon Sohn
CVPR 2017. [Paper] TPAMI 2019. [Paper] [Project Page] [Code]
Recurrent Transformer Networks for Semantic Correspondence
Seungryong Kim, Stephen Lin, Sangryul Jeon, Dongbo Min, Kwanghoon Sohn
NeurIPS 2018. [Paper] [Project Page] [Code]
Neighbourhood Consensus Networks
Ignacio Rocco, Mircea Cimpoi, Relja Arandjelović, Akihiko Torii, Tomas Pajdla, Josef Sivic
NeurIPS 2018. [Paper] [Project Page] [Code]
SFNet: Learning Object-aware Semantic Correspondence
Junghyup Lee, Dohyung Kim, Jean Ponce, Bumsub Ham
CVPR 2019. [Paper] [Project Page] [Code]
Learning to Compose Hypercolumns for Visual Correspondence
Juhong Min, Jongmin Lee, Jean Ponce, Minsu Cho
ECCV 2020. [Paper] [Project Page] [Code]
Learning Semantic Correspondence Exploiting an Object-level Prior
Junghyup Lee, Dohyung Kim, Wonkyung Lee, Jean Ponce, Bumsub Ham
TPAMI 2022. [Paper]
Weakly Supervised Learning of Semantic Correspondence through Cascaded Online Correspondence Refinement
Yiwen Huang, Yixuan Sun, Chenghang Lai, Qing Xu, Xiaomei Wang, Xuli Shen
ICCV 2023. [Paper] [Code]

Cycle/Warp Consistency-Based Methods

FlowWeb: Joint image set alignment by weaving consistent, pixel-wise correspondences
Tinghui Zhou, Yong Jae Lee, Stella X. Yu, Alexei A. Efros
CVPR 2015. [Paper] [Code]
Learning dense correspondence via 3d-guided cycle consistency
Tinghui Zhou, Philipp Krähenbühl, Mathieu Aubry, Qixing Huang, Alexei A. Efros
CVPR 2016. [Paper]
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Jun-Yan Zhu, Taesung Park, Phillip Isola, Alexei A. Efros
ICCV 2017. [Paper] [Project Page] [Code]
FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence
Seungryong Kim, Dongbo Min, Bumsub Ham, Stephen Lin, Kwanghoon Sohn
CVPR 2017, [Paper]. TPAMI 2019, [Paper] [Project Page] [Code]
Deep Semantic Matching with Foreground Detection and Cycle-Consistency
Yun-Chun Chen, Po-Hsiang Huang, Li-Yu Yu, Jia-Bin Huang, Ming-Hsuan Yang, Yen-Yu Lin
ACCV 2018. [Paper]
Semantic Matching by Weakly Supervised 2D Point Set Registration, Zakaria Laskar, Hamed R. Tavakoli, Juho Kannala
WACV 2019. [Paper]
Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation
Yun-Chun Chen, Yen-Yu Lin, Ming-Hsuan Yang, Jia-Bin Huang
TPAMI 2020. [Paper] [Project Page] [Code]
Semantic Correspondence via 2D-3D-2D Cycle
Yang You, Chengkun Li, Yujing Lou, Zhoujun Cheng, Lizhuang Ma, Cewu Lu, Weiming Wang
arXiv preprint 2020. [Paper] [Code]
GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences
Prune Truong, Martin Danelljan, Radu Timofte
CVPR 2020 Oral. [Paper] [Code]
Warp consistency for unsupervised learning of dense correspondences
Prune Truong, Martin Danelljan, Fisher Yu, Luc Van Gool
ICCV 2021. [Paper] [Code]
Probabilistic warp consistency for weakly-supervised semantic correspondences
Prune Truong, Martin Danelljan, Fisher Yu, Luc Van Gool
CVPR 2022. [Paper] [Code]

Pseudo-Label Generation-Based Methods

Probabilistic model distillation for semantic correspondence
Xin Li, Deng-Ping Fan, Fan Yang, Ao Luo, Hong Cheng, Zicheng Liu
CVPR 2021. [Paper] [Code]
Learning semantic correspondence with sparse annotations
Shuaiyi Huang, Luyu Yang, Bo He, Songyang Zhang, Xuming He, Abhinav Shrivastava
ECCV 2022. [Paper] [Project Page] [Code]
Semi-supervised learning of semantic correspondence with pseudo-labels
Jiwon Kim, Kwangrok Ryoo, Junyoung Seo, Gyuseong Lee, Daehwan Kim, Hansang Cho, Seungryong Kim
CVPR 2022. [Paper] [Code]
Weakly Supervised Learning of Semantic Correspondence through Cascaded Online Correspondence Refinement
Yiwen Huang, Yixuan Sun, Chenghang Lai, Qing Xu, Xiaomei Wang, Xuli Shen
ICCV 2023. [Paper] [Project Page] [Code]
Match me if you can: Semantic Correspondence Learning with Unpaired Images
Jiwon Kim, Byeongho Heo, Sangdoo Yun, Seungryong Kim, Dongyoon Han
ACCV 2024. [Paper] [Code]
Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels
Olaf Dünkel, Thomas Wimmer, Christian Theobalt, Christian Rupprecht, Adam Kortylewski
ICCV 2025. [Paper] [Project Page] [Code]

Other Improvements

DCTM: Discrete-Continuous Transformation Matching for Semantic Flow
Seungryong Kim, Dongbo Min, Stephen Lin, Kwanghoon Sohn
ICCV 2017. [Paper]
Discrete-Continuous Transformation Matching for Dense Semantic Correspondence
Seungryong Kim, Dongbo Min, Stephen Lin, Kwanghoon Sohn
TPAMI 2020. [Paper]
Semantic Correspondence as an Optimal Transport Problem
Yanbin Liu, Linchao Zhu, Makoto Yamada, Yi Yang
CVPR 2020. [Paper] [Code]
Unsupervised Learning of Dense Visual Representations
Pedro O. O. Pinheiro, Amjad Almahairi, Ryan Benmalek, Florian Golemo, Aaron C. Courville
NeurIPS 2020. [Paper]
Dense Contrastive Learning for Self-Supervised Visual Pre-Training
Xinlong Wang, Rufeng Zhang, Chunhua Shen, Tao Kong, Lei Li
CVPR 2021. [Paper] [Project Page]
Demystifying Unsupervised Semantic Correspondence Estimation
Mehmet Aygün, Oisin Mac Aodha
ECCV 2022. [Paper] [Project Page] [Code]
ASIC: Aligning Sparse In-The-Wild Image Collections
Kamal Gupta, Varun Jampani, Carlos Esteves, Abhinav Shrivastava, Ameesh Makadia, Noah Snavely, Abhishek Kar
ICCV 2023 Oral. [Paper] [Project Page] [Code]
Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps
Octave Mariotti, Oisin Mac Aodha, Hakan Bilen
CVPR 2024. [Paper] [Code]
Distillation of Diffusion Features for Semantic Correspondence
Frank Fundel, Johannes Schusterbauer, Vincent Tao Hu, Björn Ommer
WACV 2025. [Paper] [Project Page] [Code]
Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence
Octave Mariotti, Zhipeng Du, Yash Bhalgat, Oisin Mac Aodha, Hakan Bilen
NeurIPS 2025. [Paper]
Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence
Qiyang Qian, Hansheng Chen, Masayoshi Tomizuka, Kurt Keutzer, Qianqian Wang, Chenfeng Xu
CVPR 2025. [Paper] [Code]
Towards Robust Semantic Correspondence: A Benchmark and Insights
Wenyue Chong
arXiv preprint 2025. [Paper]