相关论文: Learning Dense Visual Descriptors using Image Augm…

Self-supervised representation learning targets to learn convnet-based image representations from unlabeled data. Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially…

Distinguishing subtle differences in attributes is valuable, yet learning to make visual comparisons remains non-trivial. Not only is the number of possible comparisons quadratic in the number of training images, but also access to images…

Despite the impressive progress brought by deep network in visual object recognition, robot vision is still far from being a solved problem. The most successful convolutional architectures are developed starting from ImageNet, a large scale…

The success of deep learning depends heavily on the availability of large datasets, but in robotic manipulation there are many learning problems for which such datasets do not exist. Collecting these datasets is time-consuming and…

Synthesizing accurate geometry and photo-realistic appearance of small scenes is an active area of research with compelling use cases in gaming, virtual reality, robotic-manipulation, autonomous driving, convenient product capture, and…

Deep learning has been achieving decent performance in computer vision requiring a large volume of images, however, collecting images is expensive and difficult in many scenarios. To alleviate this issue, many image augmentation algorithms…

Robotic fabric manipulation is challenging due to the infinite dimensional configuration space, self-occlusion, and complex dynamics of fabrics. There has been significant prior work on learning policies for specific deformable manipulation…

Although the availability of a large amount of data is usually given for granted, there are relevant scenarios where this is not the case; for instance, in the biomedical/healthcare domain, some applications require to build huge datasets…

Recent progress in deterministic prompt learning has become a promising alternative to various downstream vision tasks, enabling models to learn powerful visual representations with the help of pre-trained vision-language models. However,…

Visual localization is the task of estimating camera pose in a known scene, which is an essential problem in robotics and computer vision. However, long-term visual localization is still a challenge due to the environmental appearance…

Progress has been achieved recently in object detection given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their…

Benefited from the deep learning, image Super-Resolution has been one of the most developing research fields in computer vision. Depending upon whether using a discriminator or not, a deep convolutional neural network can provide an image…

Successful visual navigation depends upon capturing images that contain sufficient useful information. In this letter, we explore a data-driven approach to account for environmental lighting changes, improving the quality of images for use…

At the heart of the success of deep learning is the quality of the data. Through data augmentation, one can train models with better generalization capabilities and thus achieve greater results in their field of interest. In this work, we…

It is crucial to address the following issues for ubiquitous robotics manipulation applications: (a) vision-based manipulation tasks require the robot to visually learn and understand the object with rich information like dense object…

Visual scene understanding is an important capability that enables robots to purposefully act in their environment. In this paper, we propose a novel approach to object-class segmentation from multiple RGB-D views using deep learning. We…

In reinforcement learning (RL), value-based algorithms learn to associate each observation with the states and rewards that are likely to be reached from it. We observe that many self-supervised image pre-training methods bear similarity to…

Transformers have shown outstanding results for natural language understanding and, more recently, for image classification. We here extend this work and propose a transformer-based approach for image retrieval: we adopt vision transformers…

High-quality 3D reconstructions from endoscopy video play an important role in many clinical applications, including surgical navigation where they enable direct video-CT registration. While many methods exist for general multi-view 3D…

Analysis-by-synthesis has been a successful approach for many tasks in computer vision, such as 6D pose estimation of an object in an RGB-D image which is the topic of this work. The idea is to compare the observation with the output of a…