Related papers: Object-Pose Estimation With Neural Population Code…
Real-time object pose estimation is necessary for many robot manipulation algorithms. However, state-of-the-art methods for object pose estimation are trained for a specific set of objects; these methods thus need to be retrained to…
For robots to operate robustly in the real world, they should be aware of their uncertainty. However, most methods for object pose estimation return a single point estimate of the object's pose. In this work, we propose two learned methods…
This work proposes a novel pose estimation model for object categories that can be effectively transferred to previously unseen environments. The deep convolutional network models (CNN) for pose estimation are typically trained and…
Human pose estimation is a key step to action recognition. We propose a method of estimating 3D human poses from a single image, which works in conjunction with an existing 2D pose/joint detector. 3D pose estimation is challenging because…
In this paper, we present a method for real-time multi-person human pose estimation from video by utilizing convolutional neural networks. Our method is aimed for use case specific applications, where good accuracy is essential and…
Reasoning about potential occlusions is essential for robots to efficiently predict whether an object exists in an environment. Though existing work shows that a robot with active perception can achieve various tasks, it is still unclear if…
Human pose estimation from single images is a challenging problem that is typically solved by supervised learning. Unfortunately, labeled training data does not yet exist for many human activities since 3D annotation requires dedicated…
Category-level 3D pose estimation is a fundamentally important problem in computer vision and robotics, e.g. for embodied agents or to train 3D generative models. However, so far methods that estimate the category-level object pose require…
Object pose estimation is a fundamental task in computer vision and robotics, yet most methods require extensive, dataset-specific training. Concurrently, large-scale vision language models show remarkable zero-shot capabilities. In this…
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…
We present a box-free bottom-up approach for the tasks of pose estimation and instance segmentation of people in multi-person images using an efficient single-shot model. The proposed PersonLab model tackles both semantic-level reasoning…
Precise object manipulation and placement is a common problem for household robots, surgery robots, and robots working on in-situ construction. Prior work using computer vision, depth sensors, and reinforcement learning lacks the ability to…
With the aim of bridging the gap between high quality reconstruction and mobile robot motion planning, we propose an efficient system that leverages the concept of adaptive-resolution volumetric mapping, which naturally integrates with the…
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…
Visual localization is the task of accurate camera pose estimation in a known scene. It is a key problem in computer vision and robotics, with applications including self-driving cars, Structure-from-Motion, SLAM, and Mixed Reality.…
Object pose estimation has multiple important applications, such as robotic grasping and augmented reality. We present a new method to estimate the 6D pose of objects that improves upon the accuracy of current proposals and can still be…
Recent methods for 6D pose estimation of objects assume either textured 3D models or real images that cover the entire range of target poses. However, it is difficult to obtain textured 3D models and annotate the poses of objects in real…
Given the image collection of an object, we aim at building a real-time image-based pose estimation method, which requires neither its CAD model nor hours of object-specific training. Recent NeRF-based methods provide a promising solution…
With the explosive growth of available training data, single-image 3D human modeling is ahead of a transition to a data-centric paradigm. A key to successfully exploiting data scale is to design flexible models that can be supervised from…
Pose estimation of 3D objects in monocular images is a fundamental and long-standing problem in computer vision. Existing deep learning approaches for 6D pose estimation typically rely on the assumption of availability of 3D object models…