Visual localization is a fundamental task for various applications including autonomous
driving and robotics. Prior methods focus on extracting large amounts of often redundant …

Finding correspondences between images is essential for many computer vision tasks and
sparse matching pipelines have been popular for decades. However matching noise within …

Pre-training has emerged as a simple yet powerful methodology for representation learning
across various domains. However, due to the expensive training cost and limited data, pre …

Attention-based graph neural networks have made great progress in feature matching.
However, the literature lacks a comprehensive understanding of how the attention …

Visual relocalization is a key technique to autonomous driving, robotics, and
virtual/augmented reality. After decades of explorations, absolute pose regression (APR) …

Humans localize themselves efficiently in known environments by first recognizing
landmarks defined on certain objects and their spatial relationships, and then verifying the …

The 3-D reconstruction of unmanned aerial vehicle (UAV) scenes is vital for agriculture,
environmental protection, urban planning, and disaster response, to name a few. However …

Local feature matching, which aims to establish the matches between image pairs, is a
pivotal component of multiple visual applications. While current transformer-based works …

Not identical but similar objects are everywhere in the world. Examples include four-legged
animals such as dogs and cats, cars of different models, akin flowers in various colors, and …