相关论文: Can Visual Foundation Models Achieve Long-term Poi…

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…

Learning-based monocular visual odometry (VO) poses robustness, generalization, and efficiency challenges in robotics. Recent advances in visual foundation models, such as DINOv2, have improved robustness and generalization in various…

Establishing correspondences between image pairs is a long studied problem in computer vision. With recent large-scale foundation models showing strong zero-shot performance on downstream tasks including classification and segmentation,…

The task of Visual Place Recognition (VPR) is to predict the location of a query image from a database of geo-tagged images. Recent studies in VPR have highlighted the significant advantage of employing pre-trained foundation models like…

We present a novel method for scene change detection that leverages the robust feature extraction capabilities of a visual foundational model, DINOv2, and integrates full-image cross-attention to address key challenges such as varying…

Large-scale text-to-image diffusion models have shown impressive capabilities for generative tasks by leveraging strong vision-language alignment from pre-training. However, most vision-language discriminative tasks require extensive…

Visual correspondence is a crucial step in key computer vision tasks, including camera localization, image registration, and structure from motion. The most effective techniques for matching keypoints currently involve using learned sparse…

Establishing correspondences across images is a fundamental challenge in computer vision, underpinning tasks like Structure-from-Motion, image editing, and point tracking. Traditional methods are often specialized for specific…

We present a simple yet effective training-free approach for zero-shot 3D symmetry detection that leverages visual features from foundation vision models such as DINOv2. Our method extracts features from rendered views of 3D objects and…

Medical foundation models, pre-trained with large-scale clinical data, demonstrate strong performance in diverse clinically relevant applications. RETFound, trained on nearly one million retinal images, exemplifies this approach in…

Zero-shot object pose estimation enables the retrieval of object poses from images without necessitating object-specific training. In recent approaches this is facilitated by vision foundation models (VFM), which are pre-trained models that…

The integration of deep learning systems into healthcare has been hindered by the resource-intensive process of data annotation and the inability of these systems to generalize to different data distributions. Foundation models, which are…

Point tracking aims to identify the same physical point across video frames and serves as a geometry-aware representation of motion. This representation supports a wide range of applications, from robotics to augmented reality, by enabling…

Recent advances in vision-language foundational models have enabled development of systems that can perform visual understanding and reasoning tasks. However, it is unclear if these models are robust to distribution shifts, and how their…

Rapid progress is being made in developing large, pretrained, task-agnostic foundational vision models such as CLIP, ALIGN, DINOv2, etc. In fact, we are approaching the point where these models do not have to be finetuned downstream, and…

Vision Foundation Models (VFMs) and Vision Language Models (VLMs) have revolutionized computer vision by providing rich semantic and geometric representations. This paper presents a comprehensive visual comparison between CLIP based and…

Our objective in this paper is to probe large vision models to determine to what extent they 'understand' different physical properties of the 3D scene depicted in an image. To this end, we make the following contributions: (i) We introduce…

As we move towards large-scale object detection, it is unrealistic to expect annotated training data, in the form of bounding box annotations around objects, for all object classes at sufficient scale, and so methods capable of unseen…

Multi-view diffusion models have recently emerged as a powerful paradigm for novel view synthesis, yet the underlying mechanism that enables their view-consistency remains unclear. In this work, we first verify that the attention maps of…

Establishing reliable correspondences is crucial for all registration tasks, including 2D image registration, 3D point cloud registration, and 2D-3D image-to-point cloud registration. However, these tasks are often complicated by challenges…