Related papers: Rapid Pose Label Generation through Sparse Represe…
Most model-free visual object tracking methods formulate the tracking task as object location estimation given by a 2D segmentation or a bounding box in each video frame. We argue that this representation is limited and instead propose to…
We propose a single-stage, category-level 6-DoF pose estimation algorithm that simultaneously detects and tracks instances of objects within a known category. Our method takes as input the previous and current frame from a monocular RGB…
We present 6-PACK, a deep learning approach to category-level 6D object pose tracking on RGB-D data. Our method tracks in real-time novel object instances of known object categories such as bowls, laptops, and mugs. 6-PACK learns to…
Object pose estimation is a prominent task in computer vision. The object pose gives the orientation and translation of the object in real-world space, which allows various applications such as manipulation, augmented reality, etc. Various…
Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much…
In recent years, coordinate-based neural implicit representations have shown promising results for the task of Simultaneous Localization and Mapping (SLAM). While achieving impressive performance on small synthetic scenes, these methods…
Object pose estimation is a key perceptual capability in robotics. We propose a fully-convolutional extension of the PoseCNN method, which densely predicts object translations and orientations. This has several advantages such as improving…
We address the problem of robotic grasping of known and unknown objects using implicit behavior cloning. We train a grasp evaluation model from a small number of demonstrations that outputs higher values for grasp candidates that are more…
In the task of Object Recognition, there exists a dichotomy between the categorization of objects and estimating object pose, where the former necessitates a view-invariant representation, while the latter requires a representation capable…
6-DoF object pose estimation from a monocular image is challenging, and a post-refinement procedure is generally needed for high-precision estimation. In this paper, we propose a framework based on a recurrent neural network (RNN) for…
Models based on deep convolutional neural networks (CNN) have significantly improved the performance of semantic segmentation. However, learning these models requires a large amount of training images with pixel-level labels, which are very…
Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labeled datasets. However, for video semantic object segmentation, a domain where labels are scarce, effectively…
6D pose estimation of textureless objects is a valuable but challenging task for many robotic applications. In this work, we propose a framework to address this challenge using only RGB images acquired from multiple viewpoints. The core…
Sparse annotation in remote sensing object detection poses significant challenges due to dense object distributions and category imbalances. Although existing Dense Pseudo-Label methods have demonstrated substantial potential in…
We introduce a simple yet effective algorithm that uses convolutional neural networks to directly estimate object poses from videos. Our approach leverages the temporal information from a video sequence, and is computationally efficient and…
Accurate 6-DoF pose estimation of objects is critical for robots to perform precise manipulation tasks. However, for dynamic object pose estimation, conventional camera-based approaches face several major challenges, such as motion blur,…
Deep learning based image segmentation has achieved the state-of-the-art performance in many medical applications such as lesion quantification, organ detection, etc. However, most of the methods rely on supervised learning, which require a…
Solving 6D pose estimation is non-trivial to cope with intrinsic appearance and shape variation and severe inter-object occlusion, and is made more challenging in light of extrinsic large illumination changes and low quality of the acquired…
In this work, we bridge the gap between recent pose estimation and tracking work to develop a powerful method for robots to track objects in their surroundings. Motion-Nets use a segmentation model to segment the scene, and separate…
3D object pose estimation is a challenging task. Previous works always require thousands of object images with annotated poses for learning the 3D pose correspondence, which is laborious and time-consuming for labeling. In this paper, we…