EntrepreNeRF
Los Angeles, CA
Joined June 2016
- Tweets772
- Following288
- Followers5.1K
- Likes2.8K
Pinned Tweet
Happy 2025! Earlier last year I stumbled upon NVIDIA Warp, a differentiable, kernel-based framework that lets you write CUDA-like code in python. I've been making a new NeRF app with it and have found it to be extremely performant and fun to use! Enjoy this short training video. This is Warp + PyTorch + fVDB + tcnn. Enjoy!
If you’re into raytracing, this is the most exciting radiance field representation since hash grids. I feel loved. Happy Valentine’s Day! 💞
RadFoam source code has arrived! (Apache-v2)
github.com/theialab/radfoam
Belated happy Valentine's day 🥰
This is a Foliage-emulating Radiance Network, or FeRN for short. Ok just kidding it's just a NeRF of a fern I spotted on a hike but it's my post for the day. Enjoy. #WarpNeRF
Siren vibes. NeRF quality improvements are on hold for now while I work on the utterly ridiculous idea of implementing a remote websocket renderer for use in a custom Blender addon. Will it work? Probably! Will it be fast? Hell no! #WarpNeRF
Balloon Dog by Jeff Koons at the Broad Museum, Los Angeles. Continuing with static images until I can get camera movements working in the Blender addon/renderer.
Portrait of two fashionable desert nomads, trained in WarpNeRF. Without a contraction function, background collapse causes blurriness in scenes with a large amount of depth.
#WarpNeRF - Posting a NeRF a day until I get a job😄 10k steps usually trains in under 60s @ 4096 rays/sec (largely thanks to tiny-cuda-nn) and this can be improved much further. Currently working on a Blender addon to control the camera, then will fix the image quality :]
First coherent training image from a new NeRF project combining NVIDIA Warp and fVDB. Goodbye, hand-coded analytical gradients. Hello differentiable kernels! #computervision #neuralfields #nerf
Congrats @RadianceFields and @janusch_patas! Also, nice animation 😎
🎙️ The future of 3D tech is here, and I’m excited to share it with you on The @ViewDependent Podcast, the new podcast and livestream series featuring myself and @janusch_patas.
We’re talking #NeRFs, #GaussianSplatting, and how these incredible technologies are changing everything for real-life applications.
Our guest this week is @isoOH78, who has created some of the best tutorials for creating with Radiance Field platforms, such as @jawset and @playcanvas's SuperSplat.
Artwork created by @jperldev
James Perlman retweeted
3D Gaussians are moving into Ray Tracing! The newest paper from NVIDIA subs out rasterization for ray tracing.
❇️Fisheye support
❇️Depth of field
❇️Reflections and Refractions
❇️Shadows
Article: radiancefields.com/3d-gaussi…
Project Page: gaussiantracer.github.io
James Perlman retweeted
After 15+ years of exploring "Easy 3D" through SDFs, we've now put #ProjectNeo together, which you can try today in beta here: projectneo.adobe.com/
James Perlman retweeted
Sora unlocks generative large scale radiance fields and this is such a massive deal
radiancefields.com/openai-la…
James Perlman retweeted
Meet our inhouse tech Doggo "Rolo". Cinematic RGB Lighting
"More Doggo than Doggo"
Since July we've been redesigning our scanning pipeline to work with the amazing 3D Gaussian Splatting for Real-Time Radiance Field Rendering method from Inria.
github.com/graphdeco-inria/g…
IR's AeonX capture system has been designed to capture "Spatial" memories for the future.
We've built on a custom version of Inria's Sibr viewer to handle the playback of our multiple processed 4D frames.
GS has reignited our passion for 3D/4D scanning. Thank you to the team at @Inria
More content to come.
#guassiansplatting #ir #aeonx #4d #motionscanning #inria #ximea #idatronic #spatial #youth83
James Perlman retweeted
I’m talking on a panel tomorrow evening in Los Angeles about NeRFs!! It’s at this really cool gallery that’s gonna show off a lot of stuff too. You can get tickets here! Come say hi!
dice.fm/event/aqmyq-points-f…
