Tomas Cabezon Pedroso
ABSTRACT
We introduce an interactive tool called "Browsing the Latent Space" (BLS), which explores the potential of latent space visualization and interpolation in 3D generative systems for design space exploration. By visualizing and interpreting the abstract space in which the outputs produced by generative systems operate (the latent space), users gain a better understanding of how the model generates its outputs, and can explore underlying patterns and structures in the data. Using the GET3D generative model, this demonstration showcases how latent space manipulation can enhance the creative process and provides an intuitive and interactive way to explore, remix, and create new chair designs. Allowing interaction with and manipulation of the generative system’s outputs in real-time, this tool supports increased awareness of the latent space as a resource for a designer’s understanding of generative systems and creative exploration.
Supplemental Material
- [n. d.]. Three.js – JavaScript 3D Library. https://threejs.org/Google Scholar
- Mar Canet Sola and Varvara Guljajeva. 2022. Dream Painter: Exploring creative possibilities of AI-aided speech-to-image synthesis in the interactive art context. Proceedings of the ACM on Computer Graphics and Interactive Techniques 5, 4 (Sept. 2022), 1–11. https://doi.org/10.1145/3533386Google ScholarDigital Library
- Jun Gao, Tianchang Shen, Zian Wang, Wenzheng Chen, Kangxue Yin, Daiqing Li, Or Litany, Zan Gojcic, and Sanja Fidler. 2022. GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images. arxiv:2209.11163 [cs.CV]Google Scholar
- Jimpei Hitsuwari, Yoshiyuki Ueda, Woojin Yun, and Michio Nomura. 2023. Does human–AI collaboration lead to more creative art? Aesthetic evaluation of human-made and AI-generated haiku poetry. Computers in Human Behavior 139 (Feb. 2023), 107502. https://doi.org/10.1016/j.chb.2022.107502Google ScholarDigital Library
- Yang Liu, Eunice Jun, Qisheng Li, and Jeffrey Heer. 2019. Latent Space Cartography: Visual Analysis of Vector Space Embeddings. Computer Graphics Forum 38, 3 (June 2019), 67–78. https://doi.org/10.1111/cgf.13672Google ScholarCross Ref
- Eduardo Navas, Owen Gallagher, and Xtine Burrough (Eds.). 2017. The Routledge companion to remix studies. Routledge, Taylor and Francis Group, New York ; London.Google Scholar
- Aadarsh Padiyath and Brian Magerko. 2021. desAIner: Exploring the Use of ”Bad” Generative Adversarial Networks in the Ideation Process of Fashion Design. In Creativity and Cognition. ACM, Virtual Event Italy, 1–3. https://doi.org/10.1145/3450741.3466636Google ScholarDigital Library
- Yujun Shen, Jinjin Gu, Xiaoou Tang, and Bolei Zhou. 2020. Interpreting the Latent Space of GANs for Semantic Face Editing. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Seattle, WA, USA, 9240–9249. https://doi.org/10.1109/CVPR42600.2020.00926Google Scholar
- Łukasz Struski, Michał Sadowski, Tomasz Danel, Jacek Tabor, and Igor T. Podolak. 2023. Feature-Based Interpolation and Geodesics in the Latent Spaces of Generative Models. IEEE Transactions on Neural Networks and Learning Systems (2023), 1–15. https://doi.org/10.1109/TNNLS.2023.3251848 Conference Name: IEEE Transactions on Neural Networks and Learning Systems.Google ScholarCross Ref
- Meliksah Turker, Alara Dirik, and Pinar Yanardag. 2022. MIDISpace: Finding Linear Directions in Latent Space for Music Generation. In Creativity and Cognition(C&C ’22). Association for Computing Machinery, New York, NY, USA, 420–427. https://doi.org/10.1145/3527927.3532790Google ScholarDigital Library
- Laurens van der Maaten and Geoffrey Hinton. 2008. Viualizing data using t-SNE. Journal of Machine Learning Research 9 (Nov. 2008), 2579–2605.Google Scholar
- D. Wiles and Ch Dymkowski. 2013. 1000 Chairs. Cambridge University Press.Google Scholar
Index Terms
- Browsing the Latent Space: A New Approach to Interactive Design Exploration for Volumetric Generative Systems
Recommendations
Interactive Parallel Coordinates for Parametric Design Space Exploration
CHI EA '20: Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing SystemsWe present an interactive visualization based on parallel coordinates that enables comparison, generation, and modification of multiple parametric design alternatives. Such capabilities are lacking in existing tools. Initial evaluation suggests that our ...
A Visualization System for Interactive Exploration of the Cardiac Anatomy
Because of the complex and fine structure, visualization of the heart still remains a challenging task, which makes it an active research topic. In this paper, we present a visualization system for medical data, which takes advantage of the recent ...
Graph-based Latent Space Traversal for New Molecules Discovery
VINCI '23: Proceedings of the 16th International Symposium on Visual Information Communication and InteractionGenerative models provide an efficient way to analyze and understand unlabeled data, creating the latent space for data modeling and generation. Since the interpretation of latent space usually requires implicit expert knowledge, this human-centered ...
Comments