Zobrazeno 1 - 10
of 70
pro vyhledávání: '"Willis, Karl"'
Autor:
Wu, Sifan, Khasahmadi, Amir, Katz, Mor, Jayaraman, Pradeep Kumar, Pu, Yewen, Willis, Karl, Liu, Bang
Parametric Computer-Aided Design (CAD) is central to contemporary mechanical design. However, it encounters challenges in achieving precise parametric sketch modeling and lacks practical evaluation metrics suitable for mechanical design. We harness t
Externí odkaz:
http://arxiv.org/abs/2409.17457
Editing 2D icon images can require significant manual effort from designers. It involves manipulating multiple geometries while maintaining the logical or physical coherence of the objects depicted in the image. Previous language driven image editing
Externí odkaz:
http://arxiv.org/abs/2405.19636
Autor:
Xu, Xiang, Lambourne, Joseph G., Jayaraman, Pradeep Kumar, Wang, Zhengqing, Willis, Karl D. D., Furukawa, Yasutaka
This paper presents BrepGen, a diffusion-based generative approach that directly outputs a Boundary representation (B-rep) Computer-Aided Design (CAD) model. BrepGen represents a B-rep model as a novel structured latent geometry in a hierarchical tre
Externí odkaz:
http://arxiv.org/abs/2401.15563
Autor:
Tian, Yunsheng, Willis, Karl D. D., Omari, Bassel Al, Luo, Jieliang, Ma, Pingchuan, Li, Yichen, Javid, Farhad, Gu, Edward, Jacob, Joshua, Sueda, Shinjiro, Li, Hui, Chitta, Sachin, Matusik, Wojciech
The automated assembly of complex products requires a system that can automatically plan a physically feasible sequence of actions for assembling many parts together. In this paper, we present ASAP, a physics-based planning approach for automatically
Externí odkaz:
http://arxiv.org/abs/2309.16909
Autor:
Taghanaki, Saeid Asgari, Khani, Aliasghar, Pasand, Ali Saheb, Khasahmadi, Amir, Sanghi, Aditya, Willis, Karl D. D., Mahdavi-Amiri, Ali
Interpreting the learned features of vision models has posed a longstanding challenge in the field of machine learning. To address this issue, we propose a novel method that leverages the capabilities of language models to interpret the learned featu
Externí odkaz:
http://arxiv.org/abs/2309.00733
Autor:
Xu, Xiang, Jayaraman, Pradeep Kumar, Lambourne, Joseph G., Willis, Karl D. D., Furukawa, Yasutaka
This paper presents a novel generative model for Computer Aided Design (CAD) that 1) represents high-level design concepts of a CAD model as a three-level hierarchical tree of neural codes, from global part arrangement down to local curve geometry; a
Externí odkaz:
http://arxiv.org/abs/2307.00149
Autor:
Chen, Xiang 'Anthony', Burke, Jeff, Du, Ruofei, Hong, Matthew K., Jacobs, Jennifer, Laban, Philippe, Li, Dingzeyu, Peng, Nanyun, Willis, Karl D. D., Wu, Chien-Sheng, Zhou, Bolei
Through iterative, cross-disciplinary discussions, we define and propose next-steps for Human-centered Generative AI (HGAI). We contribute a comprehensive research agenda that lays out future directions of Generative AI spanning three levels: alignin
Externí odkaz:
http://arxiv.org/abs/2306.15774
Autor:
Ritchie, Daniel, Guerrero, Paul, Jones, R. Kenny, Mitra, Niloy J., Schulz, Adriana, Willis, Karl D. D., Wu, Jiajun
Procedural models (i.e. symbolic programs that output visual data) are a historically-popular method for representing graphics content: vegetation, buildings, textures, etc. They offer many advantages: interpretable design parameters, stochastic vari
Externí odkaz:
http://arxiv.org/abs/2304.10320
Autor:
Tian, Yunsheng, Xu, Jie, Li, Yichen, Luo, Jieliang, Sueda, Shinjiro, Li, Hui, Willis, Karl D. D., Matusik, Wojciech
Assembly planning is the core of automating product assembly, maintenance, and recycling for modern industrial manufacturing. Despite its importance and long history of research, planning for mechanical assemblies when given the final assembled state
Externí odkaz:
http://arxiv.org/abs/2211.03977
Autor:
Sanghi, Aditya, Fu, Rao, Liu, Vivian, Willis, Karl, Shayani, Hooman, Khasahmadi, Amir Hosein, Sridhar, Srinath, Ritchie, Daniel
Recent works have demonstrated that natural language can be used to generate and edit 3D shapes. However, these methods generate shapes with limited fidelity and diversity. We introduce CLIP-Sculptor, a method to address these constraints by producin
Externí odkaz:
http://arxiv.org/abs/2211.01427