Please use this identifier to cite or link to this item:
|Title:||Implicit Neural Sculpting|
Markov Chain Sampling
|Abstract:||In recent years, implicit surface representations through neural networks that encode the signed distance have gained popularity and have achieved state-of-the-art results in various tasks (e.g. shape representation, shape reconstruction, and learning shape priors). However, in contrast to conventional shape representations such as polygon meshes, the implicit representations cannot be easily edited and existing works that attempt to address this problem are extremely limited. In the present thesis, we propose the first method for efficient interactive editing of signed distance functions expressed through neural networks, allowing free-form editing. Inspired by 3D sculpting software for meshes, we use a brush-based framework that is intuitive and can, in the future, be used in digital art software and scientific applications. In order to localize the desired surface deformations, we regulate the network by using a copy of it to sample the previously expressed surface. We introduce a novel framework for simulating sculpting-style surface edits with efficient adaptation of network weights, in conjunction with an algorithm for uniform surface sampling. We qualitatively and quantitatively evaluate our method on various different 3D objects and under many different edits. The reported results clearly show that our method yields high accuracy, in terms of achieving the desired edits, while at the same time preserving the geometry outside the interaction areas. Code is provided on the accompanying project website https://pettza.github.io/3DNS/.|
|Appears in Collections:||Διπλωματικές Εργασίες - Theses|
Files in This Item:
|PETROS_TZATHAS_THESIS.pdf||19.87 MB||Adobe PDF||View/Open|
Items in Artemis are protected by copyright, with all rights reserved, unless otherwise indicated.