-
Chapter and Conference Paper
Novel-View Human Action Synthesis
Novel-View Human Action Synthesis aims to synthesize the movement of a body from a virtual viewpoint, given a video from a real viewpoint. We present a novel 3D reasoning to synthesize the target viewpoint. We...
-
Chapter and Conference Paper
Localisation of Defects in Volumetric Computed Tomography Scans of Valuable Wood Logs
We present a novel pipeline to efficiently localise defects in volumetric Computed Tomography (CT) scans of valuable wood logs. We couple a 2D detector applied independently on each scan slice with a multi-obj...
-
Chapter and Conference Paper
Tractogram Filtering of Anatomically Non-plausible Fibers with Geometric Deep Learning
Tractograms are virtual representations of the white matter fibers of the brain. They are of primary interest for tasks like presurgical planning, and investigation of neuroplasticity or brain disorders. Each ...
-
Chapter and Conference Paper
Self-Supervision for 3D Real-World Challenges
We consider several possible scenarios involving synthetic and real-world point clouds where supervised learning fails due to data scarcity and large domain gaps. We propose to enrich standard feature represen...
-
Chapter and Conference Paper
3D Shape Segmentation with Geometric Deep Learning
The semantic segmentation of 3D shapes with a high-density of vertices could be impractical due to large memory requirements. To make this problem computationally tractable, we propose a neural-network based a...
-
Article
A sparse coding approach for local-to-global 3D shape description
The definition of reliable shape descriptors is an essential topic for 3D object retrieval. In general, two main approaches are considered: global, and local. Global approaches are effective in describing the ...
