arXiv:2608. 11093v1 Announce Type: new Abstract: Cross-view feature matching aims to establish reliable correspondences across images with large viewpoint variations.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
Cross-view feature matching aims to establish reliable correspondences across images with large viewpoint variations. Over the past decade, the field has evolved from task-specific models toward increasingly unified and generalizable correspondence models, with recent progress further driven by the emergence of vision foundation models (VFMs).
arXiv:2606.03406v2 Announce Type: replace Abstract: Reliable correspondence estimation supports image processing and 3D vision tasks, including Structure from Motion, visual localization, and image r...
SOCO is a new benchmark for Semantic Object Correspondence that introduces a taxonomy of correspondence types and provides consistent, functionally meaningful keypoint annotations across 100 categories and over 1M correspondence pairs. It also includes keypoint language descriptions, enabling evaluation of large vision‑language models and their fine‑grained part‑level understanding. Experiments show that vision foundation backbones encode strong semantic structure but transfer correspondences poorly across related categories, LVLMs excel at text‑prompted part localization but lag in visual‑reference matching, and correspondence performance predicts dense downstream tasks more strongly than ImageNet classification.
Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains underexplored. In this work, we present Flow Any Scene...
arXiv:2609.39748v1 Announce Type: new Abstract: Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains under...
arXiv:2512.15708v2 Announce Type: replace Abstract: Foundation models are vital tools in various Computer Vision applications. They take as input a single RGB image and output a deep feature represen...