Fast and accurate single-person pose estimation, ranked 10th at CVPR'19 LIP challenge. Contains implementation of "Global Context for Convolutional Pose Machines" paper. (⭐ 170)
Progress in 3D object understanding has relied on manually canonicalized shape datasets that contain instances with consistent position and orientation (3D pose). This has made it hard to generalize these methods to in-the-wild shapes, eg., from inte...
6D object pose estimation is an important task that determines the 3D position and 3D rotation of an object in camera-centred coordinates. By utilizing such a task, one can propose promising solutions for various problems related to scene understandi...
How do we imbue robots with the ability to efficiently manipulate unseen objects and transfer relevant skills based on demonstrations? End-to-end learning methods often fail to generalize to novel objects or unseen configurations. Instead, we focus o...
In the early 1970's, Richard Stanley and Kenneth Johnson introduced and laid the groundwork for studying the order polynomial of partially ordered sets (posets). Decades later, Hamaker, Patrias, Pechenik, and Williams introduced the term "doppelgange...
Editing hairstyle is unique and challenging due to the complexity and delicacy of hairstyle. Although recent approaches significantly improved the hair details, these models often produce undesirable outputs when a pose of a source image is considera...
Jan 29, 2025 · This paper presents the design and implementation of TAPOR, a privacy-preserving, non-contact, and fully passive sensing system for accurate and robust 3D hand pose reconstruction …
A poset is called upper homogeneous, or "upho," if all of its principal order filters are isomorphic to the whole poset. In previous work of the first author, it was shown that each (finite-type N-graded) upho lattice has associated to it a finite gr...
Smile is one of the key elements in identifying emotions and present state of mind of an individual. In this work, we propose a cluster of approaches to classify posed and spontaneous smiles using deep convolutional neural network (CNN) face features...
Rotation estimation of high precision from an RGB-D object observation is a huge challenge in 6D object pose estimation, due to the difficulty of learning in the non-linear space of SO(3). In this paper, we propose a novel rotation estimation network...
The complement of an arrangement A of a finite number of affine hyperplanes in complex n-space has the structure of a poset of spaces indexed by the intersection poset, L(A). The space corresponding to G in L(A) is homotopy equivalent to the compleme...
Seams are areas of overlapping fabric formed by stitching two or more pieces of fabric together in the cut-and-sew apparel manufacturing process. In SeamPose, we repurposed seams as capacitive sensors in a shirt for continuous upper-body pose estimat...
3D hand pose estimation from images has seen considerable interest from the literature, with new methods improving overall 3D accuracy. One current challenge is to address hand-to-hand interaction where self-occlusions and finger articulation pose a...
In this paper, we explore the dynamic grasping of moving objects through active pose tracking and reinforcement learning for hand-eye coordination systems. Most existing vision-based robotic grasping methods implicitly assume target objects are stati...
The combined work of Bousquet-Mélou, Claesson, Dukes, Jelínek, Kitaev, Kubitzke and Parviainen has resulted in non-trivial bijections among ascent sequences, (2+2)-free posets, upper-triangular integer matrices, and pattern-avoiding permutations. T...
Hand pose estimation from monocular depth images is an important and challenging problem for human-computer interaction. Recently deep convolutional networks (ConvNet) with sophisticated design have been employed to address it, but the improvement ov...
We introduce CzechLynx, the first large-scale, open-access dataset for individual identification, pose estimation, and instance segmentation of the Eurasian lynx (Lynx lynx). CzechLynx contains 39,760 camera trap images annotated with segmentation ma...
We develop a system for modeling hand-object interactions in 3D from RGB images that show a hand which is holding a novel object from a known category. We design a Convolutional Neural Network (CNN) for Hand-held Object Pose and Shape estimation call...
3D hand pose estimation is a fundamental task in understanding human hands. However, accurately estimating 3D hand poses remains challenging due to the complex movement of hands, self-similarity, and frequent occlusions. In this work, we address two...
General mammal pose estimation is an important and challenging task in computer vision, which is essential for understanding mammal behaviour in real-world applications. However, existing studies are at their preliminary research stage, which focus o...