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 …
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 …
X Deng, E Liu, S Li, Y Duan… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Multi-modal image registration aims to spatially align two images from different modalities to make their feature points match with each other. Captured by different sensors, the images …
Recent research on learned visual descriptors has shown promising improvements in correspondence estimation, a key component of many 3D vision tasks. However, existing …
P Truong, M Danelljan… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Establishing dense correspondences between a pair of images is an important and general problem, covering geometric matching, optical flow and semantic correspondences. While …
H Liu, P Peng, T Chen, Q Wang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Few-shot semantic segmentation is the task of learning to locate each pixel of the novel class in the query image with only a few annotated support images. The current correlation …
Y Liu, L Zhu, M Yamada… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Establishing dense correspondences across semantically similar images is a challenging task. Due to the large intra-class variation and background clutter, two common issues occur …
We propose a novel cost aggregation network, called Cost Aggregation Transformers (CATs), to find dense correspondences between semantically similar images with additional …
S Lan, Z Yu, C Choy… - Proceedings of the …, 2021 - openaccess.thecvf.com
We introduce DiscoBox, a novel framework that jointly learns instance segmentation and semantic correspondence using bounding box supervision. Specifically, we propose a self …