Abstract
MARCO is a compact, fast model that improves semantic correspondence accuracy and generalization beyond training data by using a coarse-to-fine objective and self-distillation framework with DINOv2 and diffusion backbones.
Recent advances in semantic correspondence rely on dual-encoder architectures, combining DINOv2 with diffusion backbones. While accurate, these billion-parameter models generalize poorly beyond training keypoints, revealing a gap between benchmark performance and real-world usability, where queried points rarely match those seen during training. Building upon DINOv2, we introduce MARCO, a unified model for generalizable correspondence driven by a novel training framework that enhances both fine-grained localization and semantic generalization. By coupling a coarse-to-fine objective that refines spatial precision with a self-distillation framework, which expands sparse supervision beyond annotated regions, our approach transforms a handful of keypoints into dense, semantically coherent correspondences. MARCO sets a new state of the art on SPair-71k, AP-10K, and PF-PASCAL, with gains that amplify at fine-grained localization thresholds (+8.9 PCK@0.01), strongest generalization to unseen keypoints (+5.1, SPair-U) and categories (+4.7, MP-100), while remaining 3x smaller and 10x faster than diffusion-based approaches. Code is available at https://github.com/visinf/MARCO .
Community
MARCO (CVPR 2026 Oral) learns dense, generalizable correspondences from sparse keypoints.
It achieves state-of-the-art on standard benchmarks, improving fine-grained precision and generalizing to unseen keypoints and categories.
Built on a single DINOv2 backbone, it is 3x smaller and 10x
Get this paper in your agent:
hf papers read 2604.18267 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper