iiinova — where your digital self keeps evolving

Yash Kant

@yashkant.bsky.social

ai phd at university of toronto // prev at meta, snap research and georgia tech // web: yashkant.github.io

Yash Kant @yashkant.bsky.social · 10/06/2025

I will be at hashtag#CVPR25 in Nashville! ✨ Please come chat with me and Ethan Weber - during our poster session on Pippo, on Sat 5-7pm (Hall D)! 😊 👋 Web: yashkant.github.io/pippo CC: @ethanjohnweber.bsky.social, @igilitschenski.bsky.social

010

Reposted by Yash Kant

Igor Gilitschenski @igilitschenski.bsky.social · 03/03/2025

🧑Pippo: High-Resolution Multi-View Humans from a Single Image @yashkant.bsky.social, Ethan Weber, Jin Kyu Kim, Rawal Khirodkar, Su Zhaoen, Julieta M., Igor Gilitschenski, Shunsuke Saito, Timur Bagautdinov 3/🧵 arxiv.org/abs/2502.07785

arxiv.org

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

We present Pippo, a generative model capable of producing 1K resolution dense turnaround videos of a person from a single casually clicked photo. Pippo is a multi-view diffusion transformer and does n...

131

Reposted by Yash Kant

Igor Gilitschenski @igilitschenski.bsky.social · 03/03/2025

I am excited to share that my students @kai-he.bsky.social, @yashkant.bsky.social, Ziyi Wu, and Toshiya Yura, our previous research visitor from Sony, will present papers at #CVPR2025. 🎉 Check out their amazing work! 1/🧵

182

Reposted by Yash Kant

Alexandre Morgand, PhD @alexmrgd.bsky.social · 18/02/2025

Pippo : High-Resolution Multi-View Humans from a Single Image TL;DR: 1K Multiview Diffusion Transformer pre-trained on 3B Human images without captions; post-trained on 2.5K studio captures with pixel-aligned control via ControlMLP; generates > 5x views at inference

121