MATCHA:Towards Matching Anything

TL;DR

MATCHA introduces a unified feature model that leverages diffusion features, attention mechanisms, and object-level information to establish robust correspondences across diverse computer vision tasks, surpassing prior specialized methods.

Contribution

The paper presents the first unified feature model capable of handling geometric, semantic, and temporal matching tasks with a single approach, integrating multiple feature types for versatility.

Findings

MATCHA outperforms state-of-the-art methods across various matching tasks.

The model effectively fuses semantic and geometric features for robust correspondence.

Extensive experiments validate MATCHA's versatility and superior performance.

Abstract

Establishing correspondences across images is a fundamental challenge in computer vision, underpinning tasks like Structure-from-Motion, image editing, and point tracking. Traditional methods are often specialized for specific correspondence types, geometric, semantic, or temporal, whereas humans naturally identify alignments across these domains. Inspired by this flexibility, we propose MATCHA, a unified feature model designed to ``rule them all'', establishing robust correspondences across diverse matching tasks. Building on insights that diffusion model features can encode multiple correspondence types, MATCHA augments this capacity by dynamically fusing high-level semantic and low-level geometric features through an attention-based module, creating expressive, versatile, and robust features. Additionally, MATCHA integrates object-level features from DINOv2 to further boost generalization, enabling a single feature capable of matching anything. Extensive experiments validate that MATCHA consistently surpasses state-of-the-art methods across geometric, semantic, and temporal matching tasks, setting a new foundation for a unified approach for the fundamental correspondence problem in computer vision. To the best of our knowledge, MATCHA is the first approach that is able to effectively tackle diverse matching tasks with a single unified feature.