Summary of Pasta: Controllable Part-aware Shape Generation with Autoregressive Transformers, by Songlin Li et al.
PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers
by Songlin Li, Despoina Paschalidou, Leonidas Guibas
First submitted to arxiv on: 18 Jul 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Graphics (cs.GR); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents PASTA, a deep generative model that can generate high-quality 3D objects. The architecture consists of two components: an autoregressive transformer for generating objects as sequences of cuboidal primitives, and a blending network that composes these primitives into final meshes. The model is trained in two stages using annotated cuboidal parts and explicit 3D supervision. PASTA demonstrates shape generation from diverse inputs, including scratch, partial objects, text, and images, as well as size-guided generation and part-based variation. Compared to existing methods, PASTA generates more realistic and diverse 3D shapes while being simpler to implement and train. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary PASTA is a new way for computers to create 3D objects. Right now, it takes humans a lot of time and effort to create these objects by hand. This makes it hard to make lots of different 3D objects quickly. The PASTA team created a special computer model that can do this job faster and better than before. This model can take in some information, like text or pictures, and then use that to create new 3D objects. It’s like having a superpowerful artist who can make lots of different creations! |
Keywords
» Artificial intelligence » Autoregressive » Generative model » Transformer
