DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning

Shihuai Zhang, Zizhuo Li, Yuan Gao, Jiayi Ma
2/9/2026

No official code found. Best implementation: SuhZhang/DeMatch (13 stars, MIT, last commit 2024-06-05). 1 more below.

DOISemantic Scholar

Code Implementations(2)

SuhZhang/DeMatchPlusCommunity67%
MIT

Pytorch implementation of DeMatch++ for a comprehensive extension of CVPR'24 paper "DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning"

20PythonSep 29, 20246 months agoMIT
SuhZhang/DeMatchCommunity56%
MIT

Pytorch implementation of DeMatch for CVPR'24 paper "DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning"

132Shell, PythonMar 18, 20242 years agoMIT

Similar Papers

ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

100% match1 repo1502026

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers

99% match2026

Leveraging Proxy of Training Data for Test-Time Adaptation

99% match2026

Interaction-Based Disentanglement of Entities for Object-Centric World Models

99% match1 repo322026

MetaAT: Active Testing for Label-Efficient Evaluation of Dense Recognition Tasks

98% match2026

The Persistent Laplacian for Data Science: Evaluating Higher-Order Persistent Spectral Representations of Data

98% match1 repo82026

Cite this paper

@article{zhang2026dematch,
  title  = {DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning},
  author = {Shihuai Zhang and Zizhuo Li and Yuan Gao and Jiayi Ma},
  year   = {2026},
  doi    = {10.1109/CVPR52733.2024.01917},
  url    = {https://doi.org/10.1109/CVPR52733.2024.01917},
  journal = {CVPR 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/64f9e1cb2aff0dd17c6eb751201d204c0f9362e0.svg)](https://codeofpaper.com/paper/64f9e1cb2aff0dd17c6eb751201d204c0f9362e0)

Discussion