lukehollis

Joined 6 years ago

Karma

1,438

Submissions

133

Member since

May 1

3d graphics, engineer, founder, boxer https://github.com/lukehollis/ [email protected]

View on Hacker News

Recent submissions

Comment · 6 days ago

CarveAnything takes an input monocular image and generates a 3d model with predictive volumetric content, physics properties, and destruction mechanics for simulating cutting, lighting, and staging objects--so it may be adapted to the Halloween season.

One can use this to automate robotics policy evaluation and training on diverse objects, and more on methods is in the paper. We use a combination of semantic features and predictive per-Gaussian physics to transform individual complex objects or entire scenes to simulation environments in Isaac Lab or MuJoCo. Pumpkin carving itself is a difficult task to model accurately in these simulators.

Happy carving, HN! Glad to know of failure modes with any generated objects/carves.

CarveAnything: Image-to-volumetric material with destruction mechanics carveanything.com

2 lukehollis 6 days ago 1 comments

Show HN: Text to 3D simulation on a map (does history pretty well) with gmaps++ worldlens.co

7 lukehollis 1 year ago 0 comments

Comment · 1 year ago

Text to 3d simulation on a map. It does historical or fictitious events pretty well if it's interesting: https://mused.com/map/

I was working on world models / generative environments but without the training data available as an independent researcher, ended up focusing on building with existing geospatial data.

The same architecture of the '24 Genie paper's dynamics model is instead trained on historical data for risk analysis and creating a heatmap in the 2d map. I'll try to adapt this for a more generalizable urban mobility model as well.

Comment · 1 year ago

Thanks!

Comment · 1 year ago

you're the best of us. How'd it do? Can you share it?

Comment · 1 year ago

Ayvri is impressive, and thanks for the feedback - I hear what you're saying about the convincing replica

Comment · 1 year ago

Updated -- the geocoding was moving the map around too quickly

Comment · 1 year ago

Thanks, this should be updated for a better landing on mobile

Comment · 1 year ago

Thanks! The worst is the elevation API -- but yes, I monitored costs throughout today, it's not prohibitively expensive.