Daniel Duckworth

Introducing SMERF: a streamable, memory-efficient method for real-time exploration of large, multi-room scenes on everyday devices. Our method brings the realism of Zip-NeRF to your phone or laptop! Project page: smerf-3d.github.io ArXiv: arxiv.org/abs/2312.07541 (1/n)

I had the pleasure last month of giving slightly provocative talk at Bliss AI, a a wonderful student-run organization here in Berlin. The best part: the talk is online for everyOne to enjoy! Behold: "NeRF is dead" youtu.be/FtaC5lh8hxs?si…

Are you at #SIGGRAPH2024 and want to learn how to reconstruct meshes from multi-view images that contain details like individual strands of grass? Then come today to the "Radiance Field Processing" session at 2 p.m. in Mile High 1. binary-opacity-grid.github.io

InterNeRF: Scaling Radiance Fields via Parameter Interpolation @clintonjwang, @PeterHedman3, Polina Golland, @jon_barron, @duck tl;dr: use camera origin to assign camera region to partitioned parameter grid and compute bilinear interpolation weights arxiv.org/pdf/2406.11737

Googleがリアルタイムに高精度なレンダリングを実現する新技術「SMERF」を発表 gigazine.net/news/20231214-…

@dariel_noel @LinusEkenstam You'll have to read the paper for all of the technical details, but in short: clever use of OpenGL texture lookups + lots of model training magic.

@LinusEkenstam how does smerf achieve its real-time performance?

Did Google just kill Matterport 🤔 Introducing SMERF… I know it’s a mouthful, most impressive paper I’ve seen in this space in a long time. SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Exploration Links below ⬇️

Seeing the amazing new SMERF technology immediately made me imagine a time when we can walk around in environments like this, styled to be anything we can imagine. All happening in realtime, shaped with voice prompts or virtual paint or sculpt marks. Here's a test of using some of the SMERF demo scenes to drive a generative AI image stream in Krea.. incredible! It's like seeing the world through a new camera lens of imagination. I'll post a link to the incredible SMERF paper by @duck and his colleagues below.. what a time to be alive! #ai #art

@MartinNebelong This is absolutely wild! The future is now.

@Mi_Niemeyer I couldn't have done it without all of my amazing collaborators, especially co-first author @PeterHedman3!

Congrats Daniel and team on the great work!

@RadianceFields Want to learn more? Check out my OG explainer thread! twitter.com/duck/status/17…

SMERF from Google Research (again) achieves Zip-NeRF quality, operating at a remarkable 60fps on everyday devices like smartphones and laptops. 🔗 neuralradiancefields.io/the-merf-that-…

@supremebeme @RadianceFields This and other large scenes are captured with a DSLR camera and a fisheye lens. Approximately ~1500 photos are used. Capture takes 30~60 min.

@RadianceFields how was this scene captured? it's very clean

@AISavvyKushan Not just DeepMind! This wouldn't have been possible without my amazing colleagues in Google Research, Google Inc, and Tübingen.

Google DeepMind's researcher introduces SMERF Streamable Method for Real-Time 3D Scene Exploration a memory-efficient method for real-time exploration of large, multi-room scenes, Renders nearly indistinguishable scenes from Zip-NeRF at 60 fps or more. twitter.com/duck/status/17…

How AI reshaping industries and our daily lives? Here are the updates from Google, Grok, OpenAI, Midjourney, Stability AI and much more. (a thread) 🧵👇

@Kyrannio Don't forget my amazing collaborators at Google Research, Google Inc, and Tübingen! This was very much a team effort. More info here: twitter.com/duck/status/17…

Google DeepMind has just dropped SMERFs :) smerf-3d.github.io

@Royal790721 @wholemars No GSplats were harmed in the making of SMERF :)

SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Exploration smerf-3d.github.io

@wholemars Want to learn more? Check out my OG explainer thread: twitter.com/duck/status/17…

@GKopanas Thanks for the kind words, Georgios! I look forward to the next generation of 3DGS work as well. It's just a matter of time till 3D capture & presentation is accessible as 2D is today.

Well, there is no holy grail in science. Check out this amazing work. The quality is insane and it works on mobile too! Kudos to everyone involved!

@cpheinrich @Google The renderer is already open source! Entry point is here: github.com/smerf-3d/smerf…

These are impressive results. @Google research should open source the renderers if they want it to have impact. As we've seen with 3DGS, an abundance of renderers is necessary for widespread adoption

Thoughts NeRFs were dead? Google DeepMind just dropped SMERF — streamable, multi-room NeRFs with cm-level detail. Oh and it works realtime on mobile 🤯 It’s a sweet spot between the speed of Gaussian Splatting and the quality of Zip-NeRF. More below ⬇️

@Snosixtytwo Thank you, Bernhard :). It's an honor to hear it from you!

What an amazing push for real-time rendering! Sublime quality with a smart divide-and-conquer for seamless, high-quality novel views on your mobile phone!

@RadianceFields Big thanks to @RadianceFields for the quick write-up! Fantastic work :)