Finding correspondences between images is a fundamental problem in computer vision. In
this paper, we show that correspondence emerges in image diffusion models without any …

Text-to-image diffusion models have made significant advances in generating and editing
high-quality images. As a result, numerous approaches have explored the ability of diffusion …

Implicit neural representations (INR) have gained increasing attention in representing 3D
scenes and images, and have been recently applied to encode videos (eg, NeRV, E-NeRV) …

In this paper we address the challenge of matching semantically similar keypoints across
image pairs. Existing research indicates that the intermediate output of the UNet within the …

While pre-trained large-scale vision models have shown significant promise for semantic
correspondence their features often struggle to grasp the geometry and orientation of …

Video instance segmentation (VIS) is a challenging vision task that aims to detect segment
and track objects in videos. Conventional VIS methods rely on densely annotated object …

We present a method for joint alignment of sparse in-the-wild image collections of an object
category. Most prior works assume either ground-truth keypoint annotations or a large …

Recent self-supervised models produce visual features that are not only effective at
encoding image-level but also pixel-level semantics. They have been reported to obtain …

Recent studies show that leveraging the match-wise relationships within the 4D correlation
map yields significant improvements in establishing semantic correspondences-but at the …

Video instance segmentation requires classifying segmenting and tracking every object
across video frames. Unlike existing approaches that rely on masks boxes or category labels …