Search Results for author: Jean-Sebastien Franco

Found 11 papers, 0 papers with code

Representing motion as a sequence of latent primitives, a flexible approach for human motion modelling

no code implementations27 Jun 2022 Mathieu Marsot, Stefanie Wuhrer, Jean-Sebastien Franco, Anne Hélène Olivier

We propose a new representation of human body motion which encodes a full motion in a sequence of latent motion primitives.

A structured latent space for human body motion generation

no code implementations7 Jun 2021 Mathieu Marsot, Stefanie Wuhrer, Jean-Sebastien Franco, Stephane Durocher

We propose a framework to learn a structured latent space to represent 4D human body motion, where each latent vector encodes a full motion of the whole 3D human shape.

Human motion prediction motion prediction

Shape Reconstruction Using Volume Sweeping and Learned Photoconsistency

no code implementations ECCV 2018 Vincent Leroy, Jean-Sebastien Franco, Edmond Boyer

Our results demonstrate this ability, showing that a CNN, trained on a standard static dataset, can help recover surface details on dynamic scenes that are not perceived by traditional 2D feature based methods.

3D Shape Reconstruction

Analyzing Clothing Layer Deformation Statistics of 3D Human Motions

no code implementations ECCV 2018 Jinlong Yang, Jean-Sebastien Franco, Franck Hetroy-Wheeler, Stefanie Wuhrer

Recent capture technologies and methods allow not only to retrieve 3D model sequence of moving people in clothing, but also to separate and extract the underlying body geometry, motion component and the clothing as a geometric layer.

Multi-View Dynamic Shape Refinement Using Local Temporal Integration

no code implementations ICCV 2017 Vincent Leroy, Jean-Sebastien Franco, Edmond Boyer

We consider 4D shape reconstructions in multi-view environments and investigate how to exploit temporal redundancy for precision refinement.

Super-Resolution Temporal Sequences

Volumetric 3D Tracking by Detection

no code implementations CVPR 2016 Chun-Hao Huang, Benjamin Allain, Jean-Sebastien Franco, Nassir Navab, Slobodan Ilic, Edmond Boyer

In this paper, we propose a new framework for 3D tracking by detection based on fully volumetric representations.

Shape Animation with Combined Captured and Simulated Dynamics

no code implementations6 Jan 2016 Benjamin Allain, Li Wang, Jean-Sebastien Franco, Franck Hetroy, Edmond Boyer

Instead of using the dominant surface-based geometric representation of the capture, which is less suitable for volumetric effects, our pipeline exploits Centroidal Voronoi tessellation decompositions as unified volumetric representation of the real captured actor, which we show can be used seamlessly as a building block for all processing stages, from capture and tracking to virtual physic simulation.

An Efficient Volumetric Framework for Shape Tracking

no code implementations CVPR 2015 Benjamin Allain, Jean-Sebastien Franco, Edmond Boyer

While numerically plausible, this paradigm ignores the fact that the observed surfaces often delimit volumetric shapes, for which deformations are constrained by the volume inside the shape.

Temporal Sequences

High Resolution 3D Shape Texture from Multiple Videos

no code implementations CVPR 2014 Vagia Tsiminaki, Jean-Sebastien Franco, Edmond Boyer

To this goal we use 2D warps for all viewpoints and all temporal frames and a linear image formation model from texture to image space.

Image Super-Resolution

Cannot find the paper you are looking for? You can Submit a new open access paper.