📢A new learning-based approach to SfM: #ACEZero No img-to-img matching, optimises image-to-scene correspondences directly. Needs no pose priors. Works on unordered image sets. Efficiently handles thousands of images. Paper: https://t.co/Zc83YpoXpY Page: https://t.co/kutgb81eFV

https://t.co/9HKmv2Eh5y Also apply if you fancy topics like depth estimation, meshing, splatting, vision-language models, HCI... Niantic Research works on a wide range of topics related to the future of AR.

Niantic is looking for research interns for next summer in London. Interested in the next generation of reconstruction, mapping and visual relocalization? Apply! (And send me a DM for good measure). Let's explore what the bitter-sweet lesson can do for 3D vision. Link below.

Time to move...

After all these years, I still enjoy submitting to conferences. Is it polishing text late at night? Arguing with reviewers? Adding another publication to the pile? No. It's because each submission is a testimony, an 8-page certificate, that I learned something new. #CVPR2025

We wrote a text on how we envision the future of visual mapping: https://t.co/sIUkXMooyl So far, we have trained ~50 million ACE networks. 😎 Together, that's 150 trillion parameters... Not bad! But the future lies in going from local small models to a global large model.

Dear author, thanks for providing a bibtex entry on your project website. How about updating it with whatever venue the work has been accepted at since the original arXiv report?

As you write your #CVPR2025 papers, think of captivating first sentences. Example? "Creating noise from data is easy; creating data from noise is generative modeling." (from Song et al., ICLR21, https://t.co/5DKypA59nm)

Postdoc position available! Apply here

I love to help and suggest more reviewers. But since this involves direct communication with each candidate around their OpenReview profile, I really want to know whether it's worth my time, or whether they signed up already anyway. @CVPR #CVPR2025

Dear @CVPR, is there a way for ACs to check who is already on the reviewer lists? If not, can you please provide a way? #CVPR2025

In case you missed the latest R6D workshop at #ECCV2024, including an update on the current - and still running - BOP challenge on 6D object pose estimation: Download everything into your brain, now 👇

An ArXiv data map you can browse yourself: https://t.co/ulpNmynrRf (an early demo; please be gentle; use shift to lasso-select; click on a point to open the paper)

No Nobel for ChatGTP yet. Good choice though. I have probably read more Han Kang than Hinton 😬 At least in terms of word count.

We updated the #ACEZero repository to make it compatible with newer versions of @nerfstudioteam. We added some functions to make it easy to train Gaussian splats on top of ACE0. See our FAQ: "I want Gaussian splats from my images. What do I need to do?" https://t.co/jB8wAh38Fu

Interesting to see multiple pipelines of different sub-fields referred to as "training-free", recently. It is a re-branding of "hand-crafted" but aiming at a positive connotation, while "hand-crafted" received a negative connotation in the 2010s when everyone was moving to DL.

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

We have released the code and model weights on https://t.co/tRHmypuRFm #ECCV2024

Attending @eccvconf and looking for PhD or postdoc positions in 3D reconstruction or visual localization? Happy to talk to you :)

And we close with a bang. Shubham Tulsiani is our last invited speaker at the #MapFreeReloc workshop. #ECCV2024

Next talk at the #MapFreeReloc workshop by @SattlerTorsten. What scene representations do we have for relocation these days? #ECCV2024