Eldar Insafutdinov

303 posts

Eldar Insafutdinov

Eldar Insafutdinov

@EldarIsTyping

Computer vision researcher at Frontier AI and Robotics Lab, Amazon Ex-Postdoc @Oxford_VGG. PhD at the Max Planck Institute for Informatics. Opinions are my own.

England Katılım Mayıs 2011
889 Takip Edilen398 Takipçiler
Stan Szymanowicz
Stan Szymanowicz@StanSzymanowicz·
🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: szymanowiczs.github.io/lagernvs Code: github.com/facebookresear… Paper: arxiv.org/abs/2603.20176 Models: huggingface.co/collections/fa… Work done with @jianyuan_wang @MinghaoChen23 Christian Rupprecht and Andrea Vedaldi
English
6
32
199
30.3K
Eldar Insafutdinov
Eldar Insafutdinov@EldarIsTyping·
@oprydai It may be hard to believe this, but not everybody likes Apple aesthetics.
English
0
0
0
90
Mustafa
Mustafa@oprydai·
why would you do this when iMac exists?
Mustafa tweet media
English
574
90
5.4K
910.5K
Melissa Chen
Melissa Chen@MsMelChen·
When a brand new form of media was in its infancy 7 years ago vs. holy cow what did we do to ourselves
Melissa Chen tweet mediaMelissa Chen tweet media
English
364
111
2.3K
272.9K
Eldar Insafutdinov
Eldar Insafutdinov@EldarIsTyping·
@andreasklinger @nothing Fundamentally, it's yet another Android smartphone. There is no need for the next Apple, what's needed is a truly open platform.
English
0
0
2
107
Andreas Klinger 🦾
Andreas Klinger 🦾@andreasklinger·
🔥🇪🇺 New Video! Fun fact – the fastest-growing smartphone company ever is in Europe It's @nothing ! We went to meet their founder Carl Pei in their design studio! Nothing is different to all other phone company emulating apple. Instead of wanting to be like Apple, they want to be the next Apple. They bet on radical design, strong community, specialized products for markets (eg india), and a product culture that actually feels different. In the video: We go inside Nothing’s workshop, see how they design and build hardware, and how @getpeid thinks about the future of smartphones in the AI era. Link to the YouTube video in the reply!
English
21
29
310
37K
Hen Mazzig
Hen Mazzig@HenMazzig·
A terrorist threw a metal pole at an Israeli driver in the West Bank, thankfully missing her head and leaving her physically unharmed. This could have easily injured the driver and led to an accident on the road, however. There is so much anger and hate in this world, and violence will only make the issue worse, not better.
Hen Mazzig tweet media
English
482
68
406
39.9K
Ben Harris
Ben Harris@ahealertweets·
@tonguei66408226 @GoodwinMJ Sadly not. Natives are 36% of the London population. I describe the school next to my house now. Natives are about 52% of births in the UK this year. We are predicted to become a minority in the UK by 2060ish. I know it sounds mad, but please examine the facts. For all of us.
English
2
0
5
127
Matt Goodwin
Matt Goodwin@GoodwinMJ·
257,000 British people left Britain in 2024. This is the highest level since 1964, when records began. We all know why.
English
1.6K
1.9K
14.9K
564.7K
Eldar Insafutdinov retweetledi
Saining Xie
Saining Xie@sainingxie·
papers are kind of like movies: the first one is usually the best, and the sequels tend to get more complicated but not really more exciting. But that totally doesn’t apply to the DepthAnything series. @bingyikang's team somehow keeps making things simpler and more scalable each time. in this new version, they basically show that a strong representation encoder plus a depth-ray prediction objective is enough (you see the RAE vibes too, right?) to get solid, general spatial perception across a bunch of tasks. people often say they hate computer vision because it’s messy--too many tasks, too many data types, too many moving parts. but that’s exactly why I love it. I think the biggest AI breakthroughs are going to come quietly from vision and then suddenly leapfrog everything else, changing how AI interacts with the real world and with us. pretty soon we’ll realize vision is not a big list of tasks--it’s a perspective. a perspective about modeling continuous sensory data, building layered representations of the world, and inching toward human-like intelligence. and tbh we’re watching this happen every day, behind all the hype, as all these different '"tasks" slowly start to merge.
Bingyi Kang@bingyikang

After a year of team work, we're thrilled to introduce Depth Anything 3 (DA3)! 🚀 Aiming for human-like spatial perception, DA3 extends monocular depth estimation to any-view scenarios, including single images, multi-view images, and video. In pursuit of minimal modeling, DA3 reveals two key insights: 💎 A plain transformer (e.g., vanilla DINO) is enough. No specialized architecture. ✨ A single depth-ray representation is enough. No complex 3D tasks. Three series of models have been released: the main DA3 series, a monocular metric estimation series, and a monocular depth estimation series. The core team members, aside from me: @HaotongLin, Sili Chen, Jun Hao Liew, @donydchen. 👇(1/n) #DepthAnything3

English
5
40
519
76.1K
Ben M Freeman - בן מ פרימן
It looks like New York, the city with the largest Jewish population outside of Israel, just elected a violently anti-Jewish mayor. Let that sink in.
English
3.1K
1.1K
8.2K
448.8K
Bill Ackman
Bill Ackman@BillAckman·
Supposedly an unprecedented 2.2 million turnout with 60% above 45 years old. I am going to be an optimist and say @andrewcuomo is going to get the win. If he fails to win, it’s because @CurtisSliwa cares more about himself than NYC. Let’s never forget that. If Andrew wins, he is going to be a great mayor. Why? Because he will owe nothing to the Democratic Party and he will be working only for his legacy. He can therefore do whatever is right for NYC for the long term without worrying about the political consequences. @realDonaldTrump is going to want to work with Cuomo to Make NY Great Again, MNYGA. Say: ManyGA I think the President and Cuomo respect each other which increases the chances they will work well together. We will know supposedly by 9:30pm. Say a prayer.
English
5.6K
850
12.9K
7.2M
Konstantin Kisin
Konstantin Kisin@KonstantinKisin·
It pains me to see people dismiss the rise of socialism as being about young people being dumb and brainwashed. The truth is, young people are always dumb and brainwashed. I certainly was at 20. The question, however, is why they are increasingly susceptible to this particular type of dumbness and brainwashing. And the answer is in declining housing affordability, continued disintegration of the family, screen use/addiction and an increasingly unstable economic, social and political environment. People who have to have housemates into their mid-30s are not going to get married, have kids or do other things that make you more grounded and in touch with reality. konstantinkisin.com/p/the-real-rea…
English
1.6K
1.7K
15K
3.1M
Eldar Insafutdinov retweetledi
MrNeRF
MrNeRF@janusch_patas·
Europe Builds. Others Profit. 3D Gaussian Splatting (3DGS) is the perfect case study. It reflects both Europe’s brilliance and its chronic inability to turn that brilliance into business. Almost everything that made 3DGS possible was born in Europe. From the early breakthroughs in point-based rasterization in Switzerland to the cumulative research from Austria, Greece, and Germany executed in France, Europe built the foundation. No other continent can match that level of scientific collaboration and intellectual strength. The LichtFeld Studio bounty later confirmed it: the biggest performance leaps came straight out of European labs. The science was here. The innovation was here. The talent was here. But the business was not. When 3DGS exploded, my inbox filled with messages from US-based companies, not from Europe. In the United States, Luma AI and Polycam turned the paper into products within weeks. They did not wait for funding programs or EU consortia. They simply built. Then came China, which not only caught up in research but quickly outpaced everyone in commercialization. XGRID, DJI, and many others built thriving businesses around what Europe invented. Today, most 3DGS papers come from Chinese institutions rather than European ones. Meanwhile, the usual giants such as Meta, NVIDIA, Google, Netflix, and Tesla continue to iterate, integrate, and push forward. A thriving ecosystem of startups like World Labs leverages this technology to create new products and markets. The innovation cycle in the United States and China is fast, relentless, and market-driven. Europe, in contrast, remains bureaucratic and slow. We fund excellence and celebrate publications, but we rarely ship, even though some small startups are trying to change the status quo. Our researchers create the breakthroughs; others create the successful products. Until Europe finds a way to bridge the gap between laboratories and markets, it will remain the world’s research and development department: brilliant, underpaid, and underleveraged. Research is Europe’s comfort zone. Execution must become its strength. Video: One of my dynamic 3D Gaussian implementations based on the paper "Representing Long Volumetric Video with Temporal Gaussian Hierarchy."
English
58
160
1.3K
159K
Eldar Insafutdinov retweetledi
Visual Geometry Group (VGG)
Visual Geometry Group (VGG)@Oxford_VGG·
We are seeking a full-time Postdoctoral Research Assistant in Computer Vision to join the Visual Geometry Group (University of Oxford) to work on 3D and Spatial AI with Professor Andrea Vedaldi. The post is funded by ERC and is fixed-term for two years with a possible extension.
English
3
13
51
14.2K
Austen Allred
Austen Allred@Austen·
Engineers! We want to: Fly you to Austin Give you an apartment Clean your room Do your laundry Feed you 3x/day Help you master building with AI And give you a $200k+ job. You pay nothing, ever, no matter what. Even if you don’t take the job. apply.gauntletai.com
English
1.2K
752
13.9K
323.2K