Related papers: POISE: Pose Guided Human Silhouette Extraction und…

We present PersonaCraft, a framework for controllable and occlusion-robust full-body personalized image synthesis of multiple individuals in complex scenes. Current methods struggle with occlusion-heavy scenarios and complete body…

Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. Except for synthetic source environments, acquiring such rich supervision for each real target domain at…

Accurate estimation of the relative pose between an object and a robot hand is critical for many manipulation tasks. However, most of the existing object-in-hand pose datasets use two-finger grippers and also assume that the object remains…

This paper addresses the challenge of 3D full-body human pose estimation from a monocular image sequence. Here, two cases are considered: (i) the image locations of the human joints are provided and (ii) the image locations of joints are…

Single-view 3D shape retrieval is a challenging task that is increasingly important with the growth of available 3D data. Prior work that has studied this task has not focused on evaluating how realistic occlusions impact performance, and…

Accurate estimation of 3D human motion from monocular video requires modeling both kinematics (body motion without physical forces) and dynamics (motion with physical forces). To demonstrate this, we present SimPoE, a Simulation-based…

Reconstructing the motion of objects from videos is a key component for embodied AI and robot manipulation. While diverse approaches to object pose tracking have been studied, they rely heavily on strong external priors, such as depth data…

3D human pose estimation (HPE) is characterized by intricate local and global dependencies among joints. Conventional supervised losses are limited in capturing these correlations because they treat each joint independently. Previous…

Single-view 3D shape retrieval is a fundamental yet challenging task that is increasingly important with the growth of available 3D data. Existing approaches largely fall into two categories: those using contrastive learning to map point…

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…

In monocular 3D human pose estimation a common setup is to first detect 2D positions and then lift the detection into 3D coordinates. Many algorithms suffer from overfitting to camera positions in the training set. We propose a siamese…

Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances. However, occlusions and moving objects are still some of the major…

Human gait or walking manner is a biometric feature that allows identification of a person when other biometric features such as the face or iris are not visible. In this paper, we present a new pose-based convolutional neural network model…

Estimating the 6D object pose is an essential task in many applications. Due to the lack of depth information, existing RGB-based methods are sensitive to occlusion and illumination changes. How to extract and utilize the geometry features…

Human pose estimation from image and video is a vital task in many multimedia applications. Previous methods achieve great performance but rarely take efficiency into consideration, which makes it difficult to implement the networks on…

Multi-person pose estimation and tracking serve as crucial steps for video understanding. Most state-of-the-art approaches rely on first estimating poses in each frame and only then implementing data association and refinement. Despite the…

Facial expression editing has attracted increasing attention with the advance of deep neural networks in recent years. However, most existing methods suffer from compromised editing fidelity and limited usability as they either ignore pose…

Multi-frame human pose estimation in complicated situations is challenging. Although state-of-the-art human joints detectors have demonstrated remarkable results for static images, their performances come short when we apply these models to…

Current unsupervised 2D-3D human pose estimation (HPE) methods do not work in multi-person scenarios due to perspective ambiguity in monocular images. Therefore, we present one of the first studies investigating the feasibility of…

Depth ambiguity and joint uncertainty are the two main obstacles in obtaining accurate human pose predictions by 2D-to-3D lifting methods proposed in the literature. In particular, these issues are caused by 2D joint locations that can be…