Research Scientist at Google DeepMind, Berlin. stronglyconvex.com
Joined September 2010
- Tweets 333
- Following 149
- Followers 2,499
- Likes 613
27 Photos and videos
Pinned Tweet
13 Dec 2023
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)
21
189
842
188,014
13 Jul 2025
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=dnJ0…
1
5
3,201
Daniel Duckworth retweeted
1 Aug 2024
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.i…
31
186
18,374
Daniel Duckworth retweeted
18 Jun 2024
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
2
9
44
7,557
Daniel Duckworth retweeted
14 Dec 2023
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-s…
24
42
21,890
Daniel Duckworth retweeted
14 Dec 2023
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
15
45
301
36,299
Daniel Duckworth retweeted
13 Dec 2023
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 ⬇️
12
89
552
72,401
Daniel Duckworth retweeted
13 Dec 2023
SMERF from Google Research (again) achieves Zip-NeRF quality, operating at a remarkable 60fps on everyday devices like smartphones and laptops.
🔗 neuralradiancefields.io/the-…
4
66
346
40,147
13 Dec 2023
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)
21
189
842
188,014
13 Dec 2023
The result: a set of compact, streaming-ready submodels ready to run at up to 60 fps in your browser. The best part: you can try it out yourself: smerf-3d.github.io
(7/n)
1
1
16
3,082
13 Dec 2023
This has been a joint work with my amazing collaborators: @PeterHedman3, @chrisjreiser, @PeterZhizhin, @jfthibert, @mariolucic_, @RSzeliski, and @jon_barron
Learn more and try SMERF out yourself at smerf-3d.github.io
(8/n)
2
4
26
2,407
15 Jun 2023
From the moment NeRF was first published, the research community knew it would be something game-changing. I'm proud to be part of the team turning this amazing line of work into a real product experience!
Immersive View gives users a virtual, close-up look at indoor spaces in 3D! Learn how it uses neural radiance fields to seamlessly fuse photos to produce realistic, multidimensional reconstructions of your favorite businesses and public spaces → goo.gle/3X6L9G8
2
1
5,601
15 Jun 2023
While this blog post may only have two authors, the project itself is the hard work of a number of amazing teammates. Take a peak at the "Acknowledgments" section -- you may spot a few familiar names :)
2
2,434
Daniel Duckworth retweeted
3 Aug 2022
Code finally released for our CVPR 2022 papers (mip-NeRF 360/Ref-NeRF/RawNeRF)! You can also find links for each paper's dataset on its project page.
The code has some nice new camera utilities for larger real scenes, like this one.
github.com/google-research/m…
3 Aug 2022
We've finally released code for three of our CVPR2022 papers: mip-NeRF 360, Ref-NeRF, and RawNeRF. Instead of three separate releases, we've done something a little unusual and merged them into a single repo. Excited to see what people do with this! github.com/google-research/m…
16
95
545
15 Jun 2022
I'm stoked to be a contributor on Object SRT, a new method for unsupervised, posed-images-to-3D-scene representation and segmentation! It's crazy fast and, while far from perfect, is leaps and bounds better than anything I've seen yet :)
15 Jun 2022
So excited to share Object Scene Representation Transformer (OSRT):
OSRT learns about complex 3D scenes & decomposes them into objects w/o supervision, while rendering novel views up to 3000x faster than prior methods!
🖥️ osrt-paper.github.io
📜 arxiv.org/abs/2206.06922
1/7
7
20 Aug 2020
I'm proud to announce the release of our new paper relating Whitening, Newton's Method, and Generalization! tl;dr whitening w/o regularization significantly reduces a model's ability to generalize.
Work with @negative_result @sschoenholz @ethansdy @jaschasd
19 Aug 2020
Whitening and second order optimization both destroy information about the dataset, and can make generalization impossible: arxiv.org/abs/2008.07545 We examine what information is usable for training neural networks, and how second order methods destroy exactly that information.
3
6
20 Aug 2020
But all is not lost! We also find that *regularized* second-order optimization leads to better generalization than un-regularized second-order optimization or gradient descent.
2
3
20 Aug 2020
None of this would be possible without my amazing collaborators! @negative_result, @sschoenholz, @ethansdyer, and @jaschasd.
3