correspondence

[TPAMI'23] Unifying Flow, Stereo and Depth Estimation

Official PyTorch Implementation of "GAN-Supervised Dense Visual Alignment" (CVPR 2022 Oral, Best Paper Finalist)

Fully Convolutional Geometric Features: Fast and accurate 3D features for registration and correspondence.

[ECCV 2020] QAConv: Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting, and [CVPR 2022] GS: Graph Sampling Based Deep Metric Learning

Code release for "Canonical Surface Mapping via Geometric Cycle Consistency"

Rethinking Self-Supervised Correspondence Learning: A Video Frame-level Similarity Perspective, in ICCV 2021 (Oral)

[RAL 2024] RANSAC Back to SOTA: A Two-Stage Consensus Filtering for Real-Time 3D Registration

The first fully convolutional metric learning for geometric/semantic image correspondences.

Self-Supervised Correspondence and Optimization-Based Scene Flow (CVPR 2023)

✨ PyTorch implementation of "Cora: Correspondence-aware Image Editing Using Few-Step Diffusion", accepted at SIGGRAPH 2025.

[NeurIPS 2021] TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification

CVPR 2024, Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching

Fast Descriptors and Correspondence Propagation for Robust Global Point Cloud Registration

Correspondence Management System (Email Workflow Tracking with Instant Messaging Channels)

C++ implementation of the GMS Feature Correspondence Algorithm

Serial and parallel implementation of Dense 3D Face correspondence paper

a little program to transform a table of letters into the CMI format

Open historic data created from Benjamin Franklin's Philadelphia post office records in the collections of the American Philosophical Society.

This repository contains a collection of Digital Geometry Processing libraries to be used in achieving multiple shape correspondence.

Official Python Implementation for "CycleLK: Self-Supervised Cycle Lucas-Kanade Network for Correspondence Flow", In Submission