Learning Implicit Fields for Generative Shape Modeling — mentioned by dartmoose

Fri, 29 Jan 2021 01:58:25 GMT

My understanding of this paper (please comment/correct based on your understanding): * Instead of using a single latent feature per each implicit surface, the authors propose using a "volume" of latent features per each surface. This allows for the NNs to better capture the geometric detail while remaining relatively shallow. The result is a more accurate and faster to compute neural SDF. Contrary to the claim of another comment, the neural SDF alone is not the interesting part of this paper--the prior works points to at least three other papers that have explored the idea of representing an…

Paper and discussion history. A mention is not an endorsement.

Learning Implicit Fields for Generative Shape Modeling · HackerPapers discussions

Learning Implicit Fields for Generative Shape Modeling — mentioned by dartmoose