Sublime

Tracking Everything Everywhere All at Once paper page: https://t.co/3nmdq8KY57 present... See more

Recently, I've been working a lot on Gaussian Splatting. I built a repo for camera pose estimation using @rerundotio, @Gradio, and @prefix_dev that merges GLOMAP with hloc! 🧵More info below https://t.co/ondTtzmfzg

Enabling Versatile Controls for Video Diffusion Models https://t.co/uc16fGNYas

I wrote a datamosh camera using WebCodecs #Codepen https://t.co/OuFjVjZ1ej

Spatial Media Converter video generation is live! The desktop app now converts from RGB videos -> depth -> stereo -> Vision Pro Spatial Video (MV-HEVC). https://t.co/QkqzB5VwMC

Excited to share MonST3R! -- a simple way to estimate geometry from unposed video of dynamic scene We achieve competitive results on several downstreams (video depth, camera pose) and believe this is a promising step toward feed-forward 4D reconstruction https://t.co/4faaPaZDBb... See more

Exceedingly crispy multi-view 3D captures reconstructed beautifully (try it in browser below). Instead of the usual "deform one master model over time" approach (which breaks w/ fast motion) this FreeTimeGS paper spawns ephemeral gaussian particles as needed. They live briefly, move as neede... See more

Made some improvements to my YouTube Research Report tool. Leveraging Deepseek and o1 here. Thumbnail Builder YouTube Research YouTube Script Analyzer All will be apart of the @yapthread Playground https://t.co/pV6tqqk20x