MATCHA:Towards Matching Anything
This addresses the fundamental correspondence problem in computer vision by providing a versatile solution that can handle diverse matching tasks, which is incremental as it builds on existing diffusion model insights.
The paper tackles the problem of establishing correspondences across images for tasks like Structure-from-Motion and image editing by proposing MATCHA, a unified feature model that dynamically fuses semantic and geometric features, achieving state-of-the-art performance across geometric, semantic, and temporal matching tasks.
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.