i keep a collection of existing datasets for training nerfs or splats, all of these have a trained splat too uploaded it to 🤗huggingface huggingface.co/datasets/rishi…

we released a project a little while ago so i had to make the project page look ghibli

What if you could control the weather in any video — just like applying a filter? Meet WeatherWeaver, a video model for controllable synthesis and removal of diverse weather effects — such as 🌧️ rain, ☃️ snow, 🌁 fog, and ☁️ clouds — for any input video.

🔊New NVIDIA paper: Audio-SDS🔊 We repurpose Score Distillation Sampling (SDS) for audio, turning any pretrained audio diffusion model into a tool for diverse tasks, including source separation, impact synthesis & more. 🎧 Demos, audio examples, paper: research.nvidia.com/labs/toronto-a…

Curious about 3D Gaussians, simulation, rendering and the latest from #NVIDIA? Come to the NVIDIA Kaolin Library live-coding session at #CVPR2025, powered by a cloud GPU reserved especially for you. Wed, Jun 11, 8-noon. Bring your laptop! tinyurl.com/nv-kaolin-cvpr…

I really used to think hessian and hessian approximation given the same budget would always be a much better way to do second order. and it was hard to get much better approximations in the matrix-factorization style method budgets. not anymore

just stuck phone camera into the eyepiece of this telescope

Met some of the loveliest folks in tech in Toronto today 😄

thanks, very useful review

Heading to ACM SIGGRAPH next week. Say 👋

"everything that moves is going to be a robot" - Ming-Yu Liu at ACM SIGGRAPH