English
Related papers

Related papers: Leveraging Semantic Cues from Foundation Vision Mo…

200 papers

The extraction and matching of interest points is a prerequisite for many geometric computer vision problems. Traditionally, matching has been achieved by assigning descriptors to interest points and matching points that have similar…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Titus Cieslewski , Michael Bloesch , Davide Scaramuzza

Robust local feature detection and description are foundational tasks in computer vision. Existing methods primarily rely on single appearance cues for modeling, leading to unstable keypoints and insufficient descriptor discriminability. In…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Yang Yi , Xieyuanli Chen , Jinpu Zhang , Hui Shen , Dewen Hu

Robust robot navigation in outdoor environments requires accurate perception systems capable of handling visual challenges such as repetitive structures and changing appearances. Visual feature matching is crucial to vision-based pipelines…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Rajitha de Silva , Jonathan Cox , Marija Popovic , Cesar Cadena , Cyrill Stachniss , Riccardo Polvara

Semantic matching aims to establish pixel-level correspondences between instances of the same category and represents a fundamental task in computer vision. Existing approaches suffer from two limitations: (i) Geometric Ambiguity: Their…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Songlin Yang , Tianyi Wei , Yushi Lan , Zeqi Xiao , Anyi Rao , Xingang Pan

Feature matching is a necessary step for many computer vision and photogrammetry applications such as image registration, structure-from-motion, and visual localization. Classical handcrafted methods such as SIFT feature detection and…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Simone Gaisbauer , Prabin Gyawali , Qilin Zhang , Olaf Wysocki , Boris Jutzi

Many applications require an understanding of an image that goes beyond the simple detection and classification of its objects. In particular, a great deal of semantic information is carried in the relationships between objects. We have…

Artificial Intelligence · Computer Science 2018-08-28 Stephan Baier , Yunpu Ma , Volker Tresp

Fully-supervised CNN-based approaches for learning local image descriptors have shown remarkable results in a wide range of geometric tasks. However, most of them require per-pixel ground-truth keypoint correspondence data which is…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Iaroslav Melekhov , Zakaria Laskar , Xiaotian Li , Shuzhe Wang , Juho Kannala

Deep neural networks trained for classification have been found to learn powerful image representations, which are also often used for other tasks such as comparing images w.r.t. their visual similarity. However, visual similarity does not…

Computer Vision and Pattern Recognition · Computer Science 2019-07-24 Björn Barz , Joachim Denzler

Vision based solutions for the localization of vehicles have become popular recently. We employ an image retrieval based visual localization approach. The database images are kept with GPS coordinates and the location of the retrieved…

Computer Vision and Pattern Recognition · Computer Science 2022-02-04 Ibrahim Cinaroglu , Yalin Bastanlar

Although large-scale visual foundation models (VFMs) achieve remarkable performance in semantic understanding, they still underperform in instance-aware dense prediction tasks. They exhibit different biases in representation: for instance,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yachan Guo , JoseLuis Gomez Zurita , Danna Xue , Yi Xiao , AntonioManuel Lopez Pena

Foundation features from self-supervised vision models and text-to-image diffusion models have proven effective for semantic correspondence estimation. However, because these features are learned primarily from 2D image objectives, they…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Artur Jesslen , Olaf Dünkel , Adam Kortylewski

This work proposes a multi-image matching method to estimate semantic correspondences across multiple images. In contrast to the previous methods that optimize all pairwise correspondences, the proposed method identifies and matches only a…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Qianqian Wang , Xiaowei Zhou , Kostas Daniilidis

Finding point-wise correspondences between images is a long-standing problem in image analysis. This becomes particularly challenging for sketch images, due to the varying nature of human drawing style, projection distortions and viewport…

Computer Vision and Pattern Recognition · Computer Science 2021-01-05 Pablo Navarro , José Ignacio Orlando , Claudio Delrieux , Emmanuel Iarussi

Large-scale vision foundation models have demonstrated remarkable success across various tasks, underscoring their robust generalization capabilities. While their proficiency in two-view correspondence has been explored, their effectiveness…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Görkay Aydemir , Weidi Xie , Fatma Güney

Structured scene descriptions of images are useful for the automatic processing and querying of large image databases. We show how the combination of a semantic and a visual statistical model can improve on the task of mapping images to…

Computation and Language · Computer Science 2018-09-10 Stephan Baier , Yunpu Ma , Volker Tresp

Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…

Computer Vision and Pattern Recognition · Computer Science 2022-03-11 Taihong Xiao , Sifei Liu , Shalini De Mello , Zhiding Yu , Jan Kautz , Ming-Hsuan Yang

Purpose: To investigate whether a vision-language foundation model can enhance undersampled MRI reconstruction by providing high-level contextual information beyond conventional priors. Methods: We proposed a semantic distribution-guided…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Ruimin Feng , Xingxin He , Ronald Mercer , Zachary Stewart , Fang Liu

Visually linking matching cues is a crucial ability in daily life, such as identifying the same person in multiple photos based on their cues, even without knowing who they are. Despite the extensive knowledge that vision-language models…

Computation and Language · Computer Science 2025-07-03 Jianshu Zhang , Dongyu Yao , Renjie Pi , Paul Pu Liang , Yi R. Fung

LiDAR registration is a fundamental task in robotic mapping and localization. A critical component of aligning two point clouds is identifying robust point correspondences using point descriptors. This step becomes particularly challenging…

Robotics · Computer Science 2025-02-27 Niclas Vödisch , Giovanni Cioffi , Marco Cannici , Wolfram Burgard , Davide Scaramuzza

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 model features to understand and process single images for…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Junyi Zhang , Charles Herrmann , Junhwa Hur , Luisa Polania Cabrera , Varun Jampani , Deqing Sun , Ming-Hsuan Yang