Teaching and Talks

Teaching assistant during lab sessions: Introduction to geometric objects, learning on shapes, neural shape representations. Website

Teaching assistant during lab sessions: Introduction to computer sience, object oriented programming, web design. Java, HTML, CSS.

Teaching of first years bachelors, and assistance for exercises. Design of midterm exams.

The analysis of 3D human bodies is a fundamental problem with applications in healthcare, virtual reality, animation, and motion understanding. We introduce the main challenges of representing human shape and pose, as well as the need for geometric invariances when building shape spaces. We review classical approaches, from handcrafted descriptors, statistical body models such as SMPL to Riemannian shape analysis. In a second part, we introduce deep learning methods for 3D data such as PointNet and mesh-based CNNs. We also introduce recent techniques to build a disentangled latent representations for human shape and pose. We conclude the talk by presenting our recent learned Riemannian approach to overcome current limitations of deep learning for 3D human body analysis.

We analyze human poses and motion by introducing three sequences of easily calculated surface descriptors that are invariant under reparametrizations and Euclidean transformations. The key idea behind these descriptors is our convexity hypothesis: we suggest that most human poses are (almost) uniquely defined by their convex hull. We formulate the descriptors by associating to each finitely-triangulated surface two functions on the unit sphere: for each unit vector \( \vec{u} \) we compute the weighted area of the projection of the surface onto the plane orthogonal to \( \vec{u} \) and the length of its projection onto the line spanned by u. The \( L_2 \) norms and inner products of the projections of these functions onto the space of spherical harmonics of order \( k \) provide us with three sequences of Euclidean and reparametrization invariants of the surface. The use of these invariants reduces the comparison of 3D+time surface representations to the comparison of polygonal curves in \( \mathbb{R}^n \). The experimental results on artificial datasets are promising. Moreover, a slight modification of our method yields good results on noisy, real applications.