Semantic parametric body shape estimation from noisy depth sequences

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.

We propose a test -time adaptation for 6D object pose tracking that learns to adapt a pre -trained model to track the 6D pose of novel objects. We consider the problem of 6D object pose tracking as a 3D keypoint detection and matching task and present a mo ...

VR (Virtual Reality) is a real-time simulation that creates the subjective illusion of being in a virtual world. This thesis explores how integrating the user's body and fingers can be achieved and beneficial for the user to experience VR. At the advent of ...

Taking advantage of Capella's ability to dwell on a target for an extended period of time (nominally 30s) in its spotlight (SP) mode, an unsupervised methodology for detecting moving targets in this data is presented in this paper. By colourizing short seg ...

We present Deep MinCut (DMC), an unsupervised approach to learn node embeddings for graph -structured data. It derives node representations based on their membership in communities. As such, the embeddings directly provide insights into the graph structure ...

Advances in soft sensors coupled with machine learning are enabling increasingly capable wearable systems. Since hand motion in particular can convey useful information for developing intuitive interfaces, glove-based systems can have a significant impact ...

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 ...

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 ...

A previous study of the effect of Gadolinium doping on the dynamic polarization (DNP) of C-13 using trityls showed that the rate at which the polarization builds up is almost independent of the Gadolinium concentration, while the electron spin-lattice rela ...

The refinement and thermal stability of intermediate theta-prime (theta') precipitates are critical in the development of new high strength 2xxx series aluminium-copper (Al-Cu) alloys for high temperature applications. In this work, we use trace additions ...

Graphitic carbon nitride, g-C3N4, have been receiving intense attention the last decades due to its unique physicochemical properties, and even more importantly, due to the visible light driven photoreactivity. Hence, the design and synthesis of novel phot ...

We investigate the presence of a surface species for the active pharmaceutical ingredient (API) AZD9496 with dynamic nuclear polarization surface enhanced nuclear spectroscopy (DNP SENS). We show that using DNP we can elucidate the presence of an amorphous ...

A successful decarbonization of the European Union, coupled with a high integration of renewable energy and ambitious targets for energy efficiency, can only be reached with a significant contribution from transport. This sector currently represents a quar ...

Virtual reality (VR) is immersive not only because of visual integration, but because we can act and perform in a virtual environment (VE). Beyond the mere fact that a VR system provides images computed directly from the users' viewpoint in stereoscopy, it ...

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 ...

Lignocellulosic biomass is a potential renewable resource for production of high-value, sustainable products. Furfural is among the important bio-based chemicals in biorefineries. However, the conventional process of furfural production using a reaction-se ...

The impact of nuclear data uncertainties is studied for the reactor power and the reactivity during control rod withdrawal transients with reactivity insertions of 0.5

and 0.97

, respectively, for a PWR mini-core model. Multi-group cross sections, the mul ...

Clearwater Mesa Uames Ross Island, northeast Antarctic Peninsula) provides a unique opportunity to study solute dynamics and geochemical weathering in the pristine lacustrine systems of a high latitude environment. In order to determine major controls on t ...

Non-verbal behaviours play an important role in human communication since it can indicate human attention, serve as communication cue in interactions, or even reveal higher level personal constructs. For instance, head nod, a common non-verbal behaviour, c ...

Vision-based hand pose estimation is important in human-computer interaction. While many recent works focus on full degree-of-freedom hand pose estimation, robust estimation of global hand pose remains a challenging problem. This paper presents a novel alg ...

The thermally activated pyramidal-to-basal (PB) transition of (c + a) dislocations, transforming glissile pyramidal dissociated core structures into sessile basal dissociated ones, lies at the origin of low ductility in pure magnesium (Mg). Solute-accelera ...

Semantic parametric body shape estimation from noisy depth sequences

Chat with Graph Search

Test-time adaptation for 6D pose tracking

From finger animation to full-body embodiment of avatars with different morphologies and proportions

AN UNSUPERVISED METHOD FOR THE DETECTION OF AND TRACKING OF TARGETS IN SPOTLIGHT MODE SAR IMAGES

Deep MinCut: Learning Node Embeddings by Detecting Communities

A Wearable Smart Glove and Its Application of Pose and Gesture Detection to Sign Language Classification

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

Encoder-Decoder Models for Human Segmentation and Motion Analysis

Direct measurement of the triple spin flip rate in dynamic nuclear polarization

Coupled segregation mechanisms of Sc, Zr and Mn at theta ' interfaces enhances the strength and thermal stability of Al-Cu alloys

Coupling electrocoagulation and solar photocatalysis for electro- and photo-catalytic removal of carmoisine by Ag/graphitic carbon nitride: Optimization by process modeling and kinetic studies

High Sensitivity Detection of a Solubility Limiting Surface Transformation of Drug Particles by DNP SENS

An analysis of the impacts of green mobility strategies and technologies on different European energy system

Preventing Breaks in Embodiment in Immersive Virtual Reality

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

Exergy and exergoeconomic analyses of sustainable furfural production via reactive distillation

Uncertainty and sensitivity analysis of PWR mini-core transients in the presence of nuclear data uncertainty using non-parametric tolerance limits

Dissolved major and trace geochemical dynamics in Antarctic lacustrine systems

Accurate Nod and 3D Gaze Estimation for Social Interaction Analysis

Hough Forest With Optimized Leaves for Global Hand Pose Estimation With Arbitrary Postures

Designing high ductility in magnesium alloys