iiinova — where your digital self keeps evolving

Mark Boss

@markboss.bsky.social

1.4K followers 101 following 25 posts

I’m the Co-Head of Visual Research at Stability AI with research interests in the intersection of machine learning and computer graphics 📍Germany 🔗 markboss.me

Posts Replies Media

Mark Boss @markboss.bsky.social · 02/10/2025

Few examples from the demo. You can generate various styles from a single prompt. You can either pick semantic matching images, or not and get unexpected results. [1] unsplash.com/photos/a-boa... [2] unsplash.com/photos/mount... [3] unsplash.com/photos/man-i... [4] unsplash.com/photos/macro...

010

Mark Boss @markboss.bsky.social · 02/10/2025

This can be used for multiple applications such as color matching or diffusion guidance. Here, we showcase the diffusion process of generating a medieval house with the reference to the right.

100

Mark Boss @markboss.bsky.social · 02/10/2025

Variance in MC is quite common in computer graphics so we combined ReSTIR -- more precisely the weighted reservoir sampling -- with SWD to keep more impactful random directions in the optimization.

100

Mark Boss @markboss.bsky.social · 02/10/2025

Happy to announce: ReSWD. Sliced Wasserstein Distances are quite powerful, but they perform a Monte Carlo (MC) integration (over random directions). During an optimization this can lead to noisy gradients due to variance. Project page: reservoirswd.github.io

185

Mark Boss @markboss.bsky.social · 08/01/2025

One neat implication is that we can edit the point cloud to fix missing features or wrong scaling. We even created a small gradio component for simple edits in the demo (pypi.org/project/grad...)

An image showcasing editing of the point cloud representation to add a cup to a mug or a tail to a plush toy.

190