Related papers: A Correct-and-Certify Approach to Self-Supervise O…
Visual place recognition techniques based on deep learning, which have imposed themselves as the state-of-the-art in recent years, do not generalize well to environments visually different from the training set. Thus, to achieve top…
3D hand-object pose estimation is an important issue to understand the interaction between human and environment. Current hand-object pose estimation methods require detailed 3D labels, which are expensive and labor-intensive. To tackle the…
Training multiple deep neural networks (DNNs) and averaging their outputs is a simple way to improve the predictive performance. Nevertheless, the multiplied training cost prevents this ensemble method to be practical and efficient. Several…
For certain manipulation tasks, object pose estimation from head-mounted cameras may not be sufficiently accurate. This is at least in part due to our inability to perfectly calibrate the coordinate frames of today's high degree of freedom…
The performance of existing point cloud-based 3D object detection methods heavily relies on large-scale high-quality 3D annotations. However, such annotations are often tedious and expensive to collect. Semi-supervised learning is a good…
Accurate and robust object pose estimation for robotics applications requires verification and refinement steps. In this work, we propose to integrate hypotheses verification with object pose refinement guided by physics simulation. This…
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…
Category-level articulated object pose estimation focuses on the pose estimation of unknown articulated objects within known categories. Despite its significance, this task remains challenging due to the varying shapes and poses of objects,…
While 3D object detection and pose estimation has been studied for a long time, its evaluation is not yet completely satisfactory. Indeed, existing datasets typically consist in numerous acquisitions of only a few scenes because of the…
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…
Ensembling has proven to be a powerful technique for boosting model performance, uncertainty estimation, and robustness in supervised learning. Advances in self-supervised learning (SSL) enable leveraging large unlabeled corpora for…
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…
This paper presents a new approach for training two-stage object detection ensemble models, more specifically, Faster R-CNN models to estimate uncertainty. We propose training one Region Proposal Network(RPN) and multiple Fast R-CNN…
Obtaining accurate 3D object poses is vital for numerous computer vision applications, such as 3D reconstruction and scene understanding. However, annotating real-world objects is time-consuming and challenging. While synthetically…
The typical bottom-up human pose estimation framework includes two stages, keypoint detection and grouping. Most existing works focus on developing grouping algorithms, e.g., associative embedding, and pixel-wise keypoint regression that we…
Object pose estimation enables robots to understand and interact with their environments. Training with synthetic data is necessary in order to adapt to novel situations. Unfortunately, pose estimation under domain shift, i.e., training on…
In this paper, we proposed a pose estimation system based on rendered image training set, which predicts the pose of objects in real image, with knowledge of object category and tight bounding box. We developed a patch-based multi-class…
Detecting objects and estimating their 6D poses is essential for automated systems to interact safely with the environment. Most 6D pose estimators, however, rely on a single camera frame and suffer from occlusions and ambiguities due to…
This paper addresses the problem of cross-dataset generalization of 3D human pose estimation models. Testing a pre-trained 3D pose estimator on a new dataset results in a major performance drop. Previous methods have mainly addressed this…
To improve the generalization of 3D human pose estimators, many existing deep learning based models focus on adding different augmentations to training poses. However, data augmentation techniques are limited to the "seen" pose combinations…