Related papers: Generative Model-Based Loss to the Rescue: A Metho…
Numerous well-annotated human key-point datasets are publicly available to date. However, annotating human poses for newly collected images is still a costly and time-consuming progress. Pose distributions from different datasets share…
6D Object pose estimation is a fundamental component in robotics enabling efficient interaction with the environment. It is particularly challenging in bin-picking applications, where objects may be textureless and in difficult poses, and…
Hand pose estimation has matured rapidly in recent years. The introduction of commodity depth sensors and a multitude of practical applications have spurred new advances. We provide an extensive analysis of the state-of-the-art, focusing on…
Most sign language handshape datasets are severely limited and unbalanced, posing significant challenges to effective model training. In this paper, we explore the effectiveness of augmenting the training data of a handshape classifier by…
6D pose confidence region estimation has emerged as a critical direction, aiming to perform uncertainty quantification for assessing the reliability of estimated poses. However, current sampling-based approach suffers from critical…
Object pose estimation plays a vital role in embodied AI and computer vision, enabling intelligent agents to comprehend and interact with their surroundings. Despite the practicality of category-level pose estimation, current approaches…
In the context of imitation learning applied to dexterous robotic hands, the high complexity of the systems makes learning complex manipulation tasks challenging. However, the numerous datasets depicting human hands in various different…
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…
Autofocus is an important task for digital cameras, yet current approaches often exhibit poor performance. We propose a learning-based approach to this problem, and provide a realistic dataset of sufficient size for effective learning. Our…
We present V-HPOT, a novel approach for improving the cross-domain performance of 3D hand pose estimation from egocentric images across diverse, unseen domains. State-of-the-art methods demonstrate strong performance when trained and tested…
A challenge in training discriminative models like neural networks is obtaining enough labeled training data. Recent approaches use generative models to combine weak supervision sources, like user-defined heuristics or knowledge bases, to…
The success of deep neural networks greatly relies on the availability of large amounts of high-quality annotated data, which however are difficult or expensive to obtain. The resulting labels may be class imbalanced, noisy or human biased.…
We rethink a well-know bottom-up approach for multi-person pose estimation and propose an improved one. The improved approach surpasses the baseline significantly thanks to (1) an intuitional yet more sensible representation, which we refer…
This work considers robot keypoint estimation on color images as a supervised machine learning task. We propose the use of probabilistically created renderings to overcome the lack of labeled real images. Rather than sampling from…
Deep learning has proven to be an essential tool for medical image analysis. However, the need for accurately labeled input data, often requiring time- and labor-intensive annotation by experts, is a major limitation to the use of deep…
Neural networks are often regarded as universal equations that can estimate any function. This flexibility, however, comes with the drawback of high complexity, rendering these networks into black box models, which is especially relevant in…
Intelligent Object manipulation for grasping is a challenging problem for robots. Unlike robots, humans almost immediately know how to manipulate objects for grasping due to learning over the years. A grown woman can grasp objects more…
Trained AI systems and expert decision makers can make errors that are often difficult to identify and understand. Determining the root cause for these errors can improve future decisions. This work presents Generative Error Model (GEM), a…
Multi-person pose estimation from a 2D image is an essential technique for human behavior understanding. In this paper, we propose a human pose refinement network that estimates a refined pose from a tuple of an input image and input pose.…
Color-based two-hand 3D pose estimation in the global coordinate system is essential in many applications. However, there are very few datasets dedicated to this task and no existing dataset supports estimation in a non-laboratory…