相关论文: HyperPose: Hypernetwork-Infused Camera Pose Locali…

Maps are a key component in image-based camera localization and visual SLAM systems: they are used to establish geometric constraints between images, correct drift in relative pose estimation, and relocalize cameras after lost tracking. The…

We propose a new method for estimating the relative pose between two images, where we jointly learn keypoint detection, description extraction, matching and robust pose estimation. While our architecture follows the traditional pipeline for…

Recent research has shown growing interest in modeling hypergraphs, which capture polyadic interactions among entities beyond traditional dyadic relations. However, most existing methodologies for hypergraphs face significant limitations,…

Some recent visual-based relocalization algorithms rely on deep learning methods to perform camera pose regression from image data. This paper focuses on the loss functions that embed the error between two poses to perform deep learning…

High-precision vehicle localization with commercial setups is a crucial technique for high-level autonomous driving tasks. Localization with a monocular camera in LiDAR map is a newly emerged approach that achieves promising balance between…

Supervised deep learning with pixel-wise training labels has great successes on multi-person part segmentation. However, data labeling at pixel-level is very expensive. To solve the problem, people have been exploring to use synthetic data…

Visual localization techniques often comprise a hierarchical localization pipeline, with a visual place recognition module used as a coarse localizer to initialize a pose refinement stage. While improving the pose refinement step has been…

Unsupervised landmarks discovery (ULD) for an object category is a challenging computer vision problem. In pursuit of developing a robust ULD framework, we explore the potential of a recent paradigm of self-supervised learning algorithms,…

We present a multimodal camera relocalization framework that captures ambiguities and uncertainties with continuous mixture models defined on the manifold of camera poses. In highly ambiguous environments, which can easily arise due to…

In this work, we tackle the problem of active camera localization, which controls the camera movements actively to achieve an accurate camera pose. The past solutions are mostly based on Markov Localization, which reduces the position-wise…

This paper introduces a new architecture for human pose estimation using a multi- layer convolutional network architecture and a modified learning technique that learns low-level features and higher-level weak spatial models. Unconstrained…

Multi-animal pose estimation is essential for studying animals' social behaviors in neuroscience and neuroethology. Advanced approaches have been proposed to support multi-animal estimation and achieve state-of-the-art performance. However,…

For human pose estimation in still images, this paper proposes three semi- and weakly-supervised learning schemes. While recent advances of convolutional neural networks improve human pose estimation using supervised training data, our…

Learning good image representations that are beneficial to downstream tasks is a challenging task in computer vision. As such, a wide variety of self-supervised learning approaches have been proposed. Among them, contrastive learning has…

Performance on benchmark datasets has drastically improved with advances in deep learning. Still, cross-dataset generalization performance remains relatively low due to the domain shift that can occur between two different datasets. This…

Learning positional information of nodes in a graph is important for link prediction tasks. We propose a representation of positional information using representative nodes called landmarks. A small number of nodes with high degree…

Determining the exact latitude and longitude that a photo was taken is a useful and widely applicable task, yet it remains exceptionally difficult despite the accelerated progress of other computer vision tasks. Most previous approaches…

Recent self-supervised models have demonstrated equal or better performance than supervised methods, opening for AI systems to learn visual representations from practically unlimited data. However, these methods are typically…

Interest in physical therapy and individual exercises such as yoga/dance has increased alongside the well-being trend. However, such exercises are hard to follow without expert guidance (which is impossible to scale for personalized…

This paper revisits camera pose estimation through the lens of self-supervised pretraining, focusing on inverse-dynamics pretraining as a scalable alternative to the current trend of fully supervised training with 3D annotations.…