The intrinsic rotation invariance lies at the core of matching point clouds with handcrafted
descriptors. However, it is widely despised by recent deep matchers that obtain the rotation …

We study the problem of outlier correspondence pruning for non-rigid point cloud
registration. In rigid registration, spatial consistency has been a commonly used criterion to …

Recently, self-supervised pre-training has advanced Vision Transformers on various tasks
wrt different data modalities, eg, image and 3D point cloud data. In this paper, we explore …

The matching of 3D shapes has been extensively studied for shapes represented as surface
meshes, as well as for shapes represented as point clouds. While point clouds are a …

Successful point cloud registration relies on accurate correspondences established upon
powerful descriptors. However, existing neural descriptors either leverage a rotation-variant …

Recent advances in neural radiance fields enable novel view synthesis of photo-realistic
images in dynamic settings, which can be applied to scenarios with human animation …

Estimating the 6-DoF pose of a rigid object from a single RGB image is a crucial yet
challenging task. Recent studies have shown the great potential of dense correspondence …

Unsupervised cross-domain image retrieval (UCIR) aims to retrieve images sharing the
same category across diverse domains without relying on labeled data. Prior approaches …

We study optimal transport (OT) problem for probability measures supported on a tree metric
space. It is known that such OT problem (ie, tree-Wasserstein (TW)) admits a closed-form …

Optimal transport (OT) is a popular and powerful tool for comparing probability measures.
However, OT suffers a few drawbacks:(i) input measures required to have the same mass,(ii) …