Alberto Tono, Jiajun Wu, Gordon Wetzstein, Iro Armeni, Hariharan Subramonyam, James Landay, Martin Fischer
Deep Sketch-Based 3D Modeling (DS-3DM) explores how human sketches can be translated into rich 3D representations using modern AI techniques. This work introduces MORPHEUS, a structured design space that organizes DS-3DM methods around an Input–Model–Output framework, highlighting trends, limitations, and opportunities for user-centered 3D modeling.
We have compiled a chronological list of the primary papers referenced in this survey, presented in a format designed to facilitate long-term maintenance by the community.
We acknowledge Karen Liu, Yael Vinker, Judith Fan, Alexandra Bonnicci, Dima Smirnov, Elena Colombini and Paul Guerrero for their feedback. Furthermore, the authors thank Hannah Luxenberg-Tono, Alberto Tauiti, Simge Girgin, Eleni Alexandraki, Luc Houriez, Allie Cemalovic, Bochen Zhang, Alissa Cooperman, Andrej Krevl, Simi Aluko, Robyn Brinks Lockwood, Lisa Modifica, Veronica Augustina Bot, Samantha Bennett, Tara Srirangarajan, Collin Anthony Chen, and Yulia Gryaditskaya for their inspiration, suggestions, reviews, and support throughout the publication. The work is supported by CIFE Seed Grants, the Wu Tsai Neurosciences Institute and the Koret Human Neurosciences Community Lab (HNCL), Amazon (AWS), NVIDIA, Adobe, Google, the McCoy Family Center for Ethics in Society, and Stanford HAI. Parts of this project page were adopted from the Nerfies page.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
