Summary of Human Multi-view Synthesis From a Single-view Model:transferred Body and Face Representations, by Yu Feng et al.
Human Multi-View Synthesis from a Single-View Model:Transferred Body and Face Representations
by Yu Feng, Shunsi Zhang, Jian Shu, Hanfeng Zhao, Guoliang Pang, Chi Zhang, Hao Wang
First submitted to arxiv on: 4 Dec 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 This paper proposes an innovative framework for generating multi-view human images from a single view. The authors aim to address limitations in existing models by leveraging transferred body and facial representations. Specifically, they use a single-view model pretrained on a large-scale human dataset to develop a multi-view body representation. Additionally, they integrate transferred multimodal facial features into their trained human diffusion model to enhance detail restoration capability. Experimental evaluations demonstrate that the approach outperforms current state-of-the-art methods in multi-view human synthesis. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about creating pictures of people from different angles using just one picture. Right now, computers are not very good at doing this because they don’t have enough data to learn how humans look from different sides. The authors created a new way to teach computers by using a big collection of human images and then applying what the computer learned to create more pictures. They also added special features that help with details like facial expressions. This makes their method better than others at creating realistic pictures. |
Keywords
» Artificial intelligence » Diffusion model
