Publications

My main interest of research is to find an intuitive way of animating characters. During my thesis entitled “Performance Transfer: Animating Characters by Playing and Acting”, I’ve tried to find a method for creating expressive character animation sequences from Figurines plays. Moreover, we intrumented 3D printed figurines with HTC Vive trackers and capture their 6D trajectories, containning position and orientation data. This work tackle three problems: Creating an animation sequence using one 6D trajectory, recognizing and transfering motion qualties and create multi character animations in a storytelling context.

Coherent Mark-based Stylization of 3D Scenes at the Compositing Stage

Comptuer Graphics Forum, Eurographics 2021. Article available here. Authors Maxime Garcia (Inria / LJK / Universite Grenoble Alpes) Romain Vergne (Inria / LJK / Universite Grenoble Alpes) Mohamed-Amine Farhat (Inria / LJK / Universite Grenoble Alpes) Pierre Benard (Inria / LaBRI) Camille Nous (Laboratoire Cogitamus) Joelle Thollot (Inria / LJK / Universite Grenoble Alpes) Abstract We present a novel temporally coherent stylized rendering technique working entirely at the compositing stage.

Recognition of Laban Effort Qualities from Hand Motion

MOCO'20 - 7th International Conference on Movement and Computing, Jul 2020, Jersey City/ Virtual, United States. Article available here. Authors Maxime Garcia (Inria / LJK / Universite Grenoble Alpes) Remi Ronfard (Inria / LJK / Universite Grenoble Alpes) Abstract In this paper, we conduct a study for recognizing motion qualities in hand gestures using virtual reality trackers attached to the hand. From this 6D signal, we extract Euclidean, equi-affine and moving frame features and compare their effectiveness in the task of recognizing Laban Effort qualities.

Spatial Motion Doodles: Sketching Animation in VR Using Hand Gestures and Laban Motion Analysis

ACM Motion, Interaction and Games 2019 (MIG ‘19). Article available here. Authors Maxime Garcia (Inria / LJK / Universite Grenoble Alpes) Remi Ronfard (Inria / LJK / Universite Grenoble Alpes) Marie-Paule Cani (Ecole Polythecnique / LIX) Abstract We present a method for easily drafting expressive character animation by playing with instrumented rigid objects. We parse the input 6D trajectories (position and orientation over time) – called spatial motion doodles – into sequences of actions and convert them into detailed character animations using a dataset of parameterized motion clips which are automatically fitted to the doodles in terms of global trajectory and timing.