Advancing 3D point cloud understanding through deep transfer learning: A comprehensive survey

SS Sohail, Y Himeur, H Kheddar, A Amira, F Fadli… - Information …, 2024 - Elsevier
The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of
deep learning (DL). However, the latter faces various issues, including the lack of data or …

Gecco: Geometrically-conditioned point diffusion models

MJ Tyszkiewicz, P Fua, E Trulls - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Diffusion models generating images conditionally on text, such as Dall-E 2 and Stable
Diffusion, have recently made a splash far beyond the computer vision community. Here, we …

Partially does it: Towards scene-level fg-sbir with partial input

PN Chowdhury, AK Bhunia… - Proceedings of the …, 2022 - openaccess.thecvf.com
We scrutinise an important observation plaguing scene-level sketch research--that a
significant portion of scene sketches are" partial". A quick pilot study reveals:(i) a scene …

Learning local depth regression from defocus blur by soft-assignment encoding

R Leroy, P Trouvé-Peloux, B Le Saux, B Buat… - Applied …, 2022 - opg.optica.org
We present a novel, to the best of our knowledge, patch-based approach for depth
regression from defocus blur. Most state-of-the-art methods for depth from defocus (DFD) …

Incorporating Projective Geometry into Deep Learning

MJ Tyszkiewicz - 2024 - infoscience.epfl.ch
In this thesis we explore the applications of projective geometry, a mathematical theory of
the relation between 3D scenes and their 2D images, in modern learning-based computer …

Régression locale de la profondeur grâce au flou de défocalisation et à un réseau de neurones entraîné par soft-assignment

R Leroy, P Trouve-Peloux, B Le Saux, B Buat… - GRETSI 2022, 2022 - hal.science
Nous présentons une nouvelle approche de régression de la profondeur exploitant le flou
de défocalisation dans des patchs d'image. La plupart des méthodes dites de Depth from …