INST-Sculpt: Interactive Stroke-based Neural SDF Sculpting
This provides a valuable editing tool for the graphics and modeling community by enabling intuitive sculpting on neural SDFs, addressing a gap compared to traditional mesh-based tools like ZBrush.
The paper tackles the problem of directly editing neural implicit 3D representations, which is challenging due to the complex link between model weights and surface regions, by introducing a framework for interactive stroke-based sculpting that allows intuitive shape manipulation without switching representations, achieving smooth deformations along user-defined curves.
Recent advances in implicit neural representations have made them a popular choice for modeling 3D geometry, achieving impressive results in tasks such as shape representation, reconstruction, and learning priors. However, directly editing these representations poses challenges due to the complex relationship between model weights and surface regions they influence. Among such editing tools, sculpting, which allows users to interactively carve or extrude the surface, is a valuable editing operation to the graphics and modeling community. While traditional mesh-based tools like ZBrush facilitate fast and intuitive edits, a comparable toolkit for sculpting neural SDFs is currently lacking. We introduce a framework that enables interactive surface sculpting edits directly on neural implicit representations. Unlike previous works limited to spot edits, our approach allows users to perform stroke-based modifications on the fly, ensuring intuitive shape manipulation without switching representations. By employing tubular neighborhoods to sample strokes and custom brush profiles, we achieve smooth deformations along user-defined curves, providing precise control over the sculpting process. Our method demonstrates that intricate and versatile edits can be made while preserving the smooth nature of implicit representations.