- publication
- SIGGRAPH 2022 (journal paper)
- authors
- Amir Hertz, Or Perel, Raja Giryes, Olga Sorkine-Hornung, Daniel Cohen-Or
Design exploration with SPAGHETTI: Using our method, the user can easily compose new shapes (in grey) out of parts (in green) taken from reference shapes or make further local adjustments of selected parts (in red).
abstract
Neural implicit fields are quickly emerging as an attractive representation for learning based techniques. However, adopting them for 3D shape modeling and editing is challenging. We introduce a method for Editing Implicit Shapes Through Part Aware GeneraTion, permuted in short as SPAGHETTI. Our architecture allows for manipulation of implicit shapes by means of transforming, interpolating and combining shape segments together, without requiring explicit part supervision. SPAGHETTI disentangles shape part representation into extrinsic and intrinsic geometric information. This characteristic enables a generative framework with part-level control. The modeling capabilities of SPAGHETTI are demonstrated using an interactive graphical interface, where users can directly edit neural implicit shapes.
downloads
video
acknowledgments
This work is supported in part by the European Research Council (ERC) Consolidator grant no. 101003104 and Starting grant no. 757497, by the Israel Science Foundation grant no. 2492/20 and by the Innovation Programme grant no. 101003104.