相关论文: VPN++: Rethinking Video-Pose embeddings for unders…

Humans naturally perceive a 3D scene in front of them through accumulation of information obtained from multiple interconnected projections of the scene and by interpreting their correspondence. This phenomenon has inspired artificial…

We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from RGB video sequences. Our approach proceeds along two stages. In the first, we run a real-time 2D pose detector to determine…

We propose a three-stage 6 DoF object detection method called DPODv2 (Dense Pose Object Detector) that relies on dense correspondences. We combine a 2D object detector with a dense correspondence estimation network and a multi-view pose…

We tackle the task of multi-view, multi-person 3D human pose estimation from a limited number of uncalibrated depth cameras. Recently, many approaches have been proposed for 3D human pose estimation from multi-view RGB cameras. However,…

In this paper, we propose a novel Attentive Multi-View Deep Subspace Nets (AMVDSN), which deeply explores underlying consistent and view-specific information from multiple views and fuse them by considering each view's dynamic contribution…

Human perception of surroundings is often guided by the various poses present within the environment. Many computer vision tasks, such as human action recognition and robot imitation learning, rely on pose-based entities like human…

Pose registration is critical in vision and robotics. This paper focuses on the challenging task of initialization-free pose registration up to 7DoF for homogeneous and heterogeneous measurements. While recent learning-based methods show…

3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields. In this paper, we propose Point-Voxel Region-based Convolution Neural Networks (PV-RCNNs) for 3D object…

Activity detection is one of the attractive computer vision tasks to exploit the video streams captured by widely installed cameras. Although achieving impressive performance, conventional activity detection algorithms are usually designed…

In this work, we introduce a novel method for calculating the 6DoF pose of an object using a single RGB-D image. Unlike existing methods that either directly predict objects' poses or rely on sparse keypoints for pose recovery, our approach…

While natural language is commonly used to guide embodied agents, the inherent ambiguity and verbosity of language often hinder the effectiveness of language-guided navigation in complex environments. To this end, we propose Visual Prompt…

We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints. Learning such universal models requires training images…

An accurate and robust large-scale localization system is an integral component for active areas of research such as autonomous vehicles and augmented reality. To this end, many learning algorithms have been proposed that predict 6DOF…

Analysis-by-synthesis has been a successful approach for many tasks in computer vision, such as 6D pose estimation of an object in an RGB-D image which is the topic of this work. The idea is to compare the observation with the output of a…

We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference. 3D convolutional neural networks (CNNs) are accurate at video recognition but…

Despite recent advances in facial recognition, there remains a fundamental issue concerning degradations in performance due to substantial perspective (pose) differences between enrollment and query (probe) imagery. Therefore, we propose a…

Recently, pose-based action recognition has gained more and more attention due to the better performance compared with traditional appearance-based methods. However, there still exist two problems to be further solved. First, existing…

In this paper, we present a novel, end-to-end 6D object pose estimation method that operates on RGB inputs. Our approach is composed of 2 main components: the first component classifies the objects in the input image and proposes an initial…

Video depth estimation is essential for providing 3D scene structure in applications ranging from autonomous driving to mixed reality. Current end-to-end video depth models have established state-of-the-art performance. Although current…

The goal of this work is to replace objects in an RGB-D scene with corresponding 3D models from a library. We approach this problem by first detecting and segmenting object instances in the scene using the approach from Gupta et al. [13].…