CVPR2025

Pippo: High-Resolution Multi-View Humans from a Single Image

Yash Kant, Ethan Weber, Jin Kyu Kim, Rawal Khirodkar, Su Zhaoen, Julieta Martinez, Igor Gilitschenski, Shunsuke Saito, Timur M. Bagautdinov

Abstract

Figure 1. Pippo produces high-resolution, multi-view, studio-quality images from a single image. First row shows full-body generation of an unseen subject captured from an iPhone picture. Second and third rows show face-only and partial full-body input images from unseen studio subject(s) to novel views respectively. All visuals are at 1K resolution.