![]() ![]() We discretize maps via common triangulations that approximate the input meshes while remaining in bijective correspondence to them. In contrast to previous approaches, we decouple the resolution at which a map is represented from the resolution of the input meshes. We present a new method to compute continuous and bijective maps (surface homeomorphisms) between two or more genus-0 triangle meshes. Furthermore, we show how boundary sensitivity helps to optimize andĬonstrain objectives (such as surface area and volume), which are difficult toĬompute without first converting to another representation, such as a mesh. Our method is agnostic to the model its training and updates the NN Of the shape to change according to some prior, such as semantics or deformation Prescribing the deformation only locally allows the rest Geometric editing: finding a parameter update that best approximates a globally Learnable parameter and study achievable deformations. This allows to interpret the effect of each Motivated by this, we leverage boundary sensitivity to express how perturbations Neural representations do not allow the user to exert intuitive control over the shape. ![]() ![]() Compared to classic geometry representations, however, To their ability to compactly store detailed and smooth shapes and easily undergo Neural fields are receiving increased attention as a geometric representation due
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |