From Canonical Poses to 3D Motion Capture Using a Single Camera

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Representing and reconstructing 3D deformable shapes are two tightly linked problems that have long been studied within the computer vision field. Deformable shapes are truly ubiquitous in the real world, whether be it specific object classes such as human ...

Transportation, which deals with moving people and goods around, has a clear impact on the economic development of our society and our well-being. Traditionally, transportation was studied and analyzed using expensive sensors, such as induction loops, that ...

We address the detection, tracking, and relative localization of the agents of a drone swarm from a human perspective using a headset equipped with a single camera and an Inertial Measurement Unit (IMU). We train and deploy a deep neural network detector o ...

Non-Rigid Structure-from-Motion (NRSfM) reconstructs a deformable 3D object from keypoint correspondences established between monocular 2D images. Current NRSfM methods lack statistical robustness, which is the ability to cope with correspondence errors. T ...

LiftPose3D infers three-dimensional poses from two-dimensional data or from limited three-dimensional data. The approach is illustrated for videos of behaving Drosophila, mice, rats and macaques. ...

Detecting people from 2D images and analyzing their motion in 3D have been long standing computer vision problems central to numerous applications such as autonomous driving and athletic training. Recently, with the availability of large amounts of trainin ...

Decentralized deployment of drone swarms usually relies on inter-agent communication or visual markers that are mounted on the vehicles to simplify their mutual detection. This letter proposes a vision-based detection and tracking algorithm that enables gr ...

Object-centric learning has gained significant attention over the last years as it can serve as a powerful tool to analyze complex scenes as a composition of simpler entities. Well-established tasks in computer vision, such as object detection or instance ...

Perceiving humans in the context of Intelligent Transportation Systems (ITS) often relies on multiple cameras or expensive LiDAR sensors. In this work, we present a new cost-effective vision-based method that perceives humans' locations in 3D and their bod ...

Many robotics problems are formulated as optimization problems. However, most optimization solvers in robotics are locally optimal and the performance depends a lot on the initial guess. For challenging problems, the solver will often get stuck at poor loc ...

An innovative photogrammetric pipeline has been developed by INAF-Padova for the processing of the stereo images from the CaSSIS (Colour and Stereo Imaging System) (Thomas et al., 2014). CaSSIS is the multispectral stereo push frame camera on board ExoMars ...

In this paper, we introduce a new solution and underlying architecture that allows remote participants to interact with hosts in a broadcast scenario. To achieve this, background extraction is first applied to video received from remote participants to ext ...

The human face plays an essential role in social interactions as it brings information about someone's identity, state of mind, or mood. People are, by nature, very good at catching this non-spoken information. Therefore, scientists have been interested in ...

Animals are capable of extreme agility, yet understanding their complex dynamics, which have ecological, biomechanical and evolutionary implications, remains challenging. Being able to study this incredible agility will be critical for the development of n ...

There are many approaches to weakly-supervised training of networks to segment 2D images. By contrast, existing approaches to segmenting volumetric images rely on full-supervision of a subset of 2D slices of the 3D volume. We propose an approach to volume ...

Three-dimensional (3D) knee angle measurement is one of the key measures in human gait analysis. Inertial sensor capable of measuring joint motion under unconstrained conditions is a practical tool for clinical evaluation and rehabilitation. An inertial me ...

In airborne laser scanning a high-frequency trajectory solution is typically determined from inertial sensors and employed to directly geo-reference the acquired laser points. When low-cost MEMS inertial sensors are used, such as in lightweight unmanned ae ...

In this paper we propose an unsupervised feature extraction method to capture temporal information on monocular videos, where we detect and encode subject of interest in each frame and leverage contrastive self-supervised (CSS) learning to extract rich lat ...

For the past twenty years, the adoption of Virtual Geographic Environments is thriving. This democratization is due to numerous new opportunities offered by this medium. However, in participatory urban planning these interactive 3D geovisualizations are st ...

From Canonical Poses to 3D Motion Capture Using a Single Camera

Chat with Graph Search

Learning to Represent and Reconstruct 3D Deformable Objects

Visual Scene Understanding for Transportation: From Detecting Objects To Relationships

Tracking and Relative Localization of Drone Swarms With a Vision-Based Headset

Robust Isometric Non-Rigid Structure-From-Motion

LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals

Encoder-Decoder Models for Human Segmentation and Motion Analysis

Vision-based Drone Flocking in Outdoor Environments

Unsupervised Visual Entity Abstraction towards 2D and 3D Compositional Models

Perceiving Humans: from Monocular 3D Localization to Social Distancing

Memory of Motion for Initializing Optimization in Robotics

3DPD: A photogrammetric pipeline for a PUSH frame stereo cameras

AI-based telepresence for broadcast applications

Model-based 3D Face Reconstruction

AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wild

Weakly Supervised Volumetric Image Segmentation with Deformed Templates

Biomechanical Ambulatory Assessment of 3D Knee Angle Using Novel Inertial Sensor-Based Technique

On the benefit of concurrent adjustment of active and passive optical sensors with GNSS & raw inertial data

Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation

How do users interact with Virtual Geographic Environments? Users' behavior evaluation in urban participatory planning