Generating robust and reliable correspondences across images is a fundamental task for a
diversity of applications. To capture context at both global and local granularity, we propose …

We present a novel method for efficiently producing semi-dense matches across images.
Previous detector-free matcher LoFTR has shown remarkable matching capability in …

Feature matching is an important computer vision task that involves estimating
correspondences between two images of a 3D scene and dense methods estimate all such …

We present a novel method for local image feature matching. Instead of performing image
feature detection, description, and matching sequentially, we propose to first establish pixel …

Few-shot semantic segmentation aims at learning to segment a target object from a query
image using only a few annotated support images of the target class. This challenging task …

We study the problem of extracting correspondences between a pair of point clouds for
registration. For correspondence retrieval, existing works benefit from matching sparse …

As a fundamental and critical task in various visual applications, image matching can identify
then correspond the same or similar structure/content from two or more images. Over the …

Local feature matching is a computationally intensive task at the subpixel level. While
detector-based methods coupled with feature descriptors struggle in low-texture scenes …

Keypoint detection & descriptors are foundational technologies for computer vision tasks like
image matching, 3D reconstruction and visual odometry. Hand-engineered methods like …

Finding local features that are repeatable across multiple views is a cornerstone of sparse
3D reconstruction. The classical image matching paradigm detects keypoints per-image …