BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Enhanced reflections in neural rendering of signed distance functi
 ons
DTSTART:20230615T090000
DTEND:20230615T110000
DTSTAMP:20260511T120213Z
UID:946512535e143355635a38e43f7ca5eb39d2293a11e58cbdfe783253
CATEGORIES:Conferences - Seminars
DESCRIPTION:Corentin Dumery\nEDIC candidacy exam\nExam president: Prof. We
 nzel Jakob\nThesis advisor: Prof. Pascal Fua\nCo-examiner: Prof. Alexandre
  Alahi\n\nAbstract\nWhile significant progress has been made in reconstruc
 ting 3D scenes\, the ability to interpret and interact with the reconstruc
 ted environment remains a challenge. Neural implicit surfaces\, in particu
 lar\, have emerged as powerful tools for reconstruction but pose difficult
 ies in handling and interpreting.\n\nOur proposed approach focuses on addr
 essing this challenge by incorporating semantic knowledge into neural radi
 ance fields. By developing a framework that can infer and incorporate sema
 ntic information\, we aim to enable systems such as autonomous robots to e
 ffectively make sense of the reconstructed scene and interact with it.\n\n
 Background papers\n\n	NeuS: Learning Neural Implicit Surfaces by Volume Re
 ndering for Multi-view Reconstruction\, NeurIPS 2021\, Peng Wang\, Lingjie
  Liu\, Yuan Liu\, Christian Theobalt\, Taku Komura\, Wenping Wang\n	Differ
 entiable Signed Distance Function Rendering\, SIGGRAPH 2022\, Delio Vicin
 i\, Sébastien Speierer\, Wenzel Jakob (president of the jury)\n	NeSF: Neu
 ral Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes\,
  TMLR22\, Suhani Vora\, Noha Radwan\, Klaus Greff\, Henning Meyer\, Kyle G
 enova\, Mehdi S. M. Sajjadi\, Etienne Pot\, Andrea Tagliasacchi\, Daniel D
 uckworth\n
LOCATION:BC 229 https://plan.epfl.ch/?room==BC%20229
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR