Loading Now

Summary of Pomo3d: 3d-aware Portrait Accessorizing and More, by Tzu-chieh Liu et al.


Pomo3D: 3D-Aware Portrait Accessorizing and More

by Tzu-Chieh Liu, Chih-Ting Liu, Shao-Yi Chien

First submitted to arxiv on: 22 Sep 2024

Categories

  • Main: Computer Vision and Pattern Recognition (cs.CV)
  • Secondary: Artificial Intelligence (cs.AI)

     Abstract of paper      PDF of paper


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 proposed Pomo3D framework enables 3D portrait manipulation with fine-grained editing capabilities. It allows avatars to wear multiple accessories simultaneously, overcoming limitations in existing methods that often cause identity shifts or fail to generate additional objects. The framework consists of the Scribble2Accessories module, which creates 3D accessories from user-drawn maps, and a bias-conscious mapper to mitigate real-world dataset biases. Pomo3D also offers global and local editing options for portrait geometry, texture, and stylization, elevating neural portrait editing.
Low GrooveSquid.com (original content) Low Difficulty Summary
Pomo3D is a new way to edit portraits in 3D. It lets people create fun and fashionable virtual characters by adding accessories like hats or jewelry. Right now, most methods only allow one accessory at a time and can change the character’s appearance too much. Pomo3D solves this problem by letting users add multiple accessories while keeping the character looking like themselves. The system also includes tools for editing portraits, such as changing their shape or color.

Keywords

» Artificial intelligence