Filippo Aleotti

Machine Learning Engineer @ Niantic

[Filippo Aleotti @AleottiFilippo]

@KadirYilmaz_CV @adr_kruse @dcdegeus @BastianLeibe Congrats!

[Filippo Aleotti @AleottiFilippo]

Remember to recharge

[Filippo Aleotti @AleottiFilippo]

🙏🙏

[#CVPR2026 @CVPR]

We are grateful to all of the 17,491 reviewers who helped make #CVPR2026 possible. We are especially pleased to recognize the following Outstanding Reviewers, whose high-quality reviews (as judged by their Area Chairs) placed them among the top 5% of reviewers.

[Filippo Aleotti @AleottiFilippo]

Great book, rude bookmark 🤗

[Sergio Izquierdo @serizba]

🔍Looking for a multi-view depth method that just works?

We're excited to share MVSAnywhere, which we will present at #CVPR2025. MVSAnywhere produces sharp depths, generalizes and is robust to all kind of scenes, and it's scale agnostic.

More info:
https://t.co/esbaLbsRF4

[Guillermo Garcia-Hernando @gui_ggh]

👋Would you like more accurate 3D camera-space hand mesh predictions? Check our new #ECCV2024 work: "HandDGP: Camera-Space Hand Mesh Prediction with Differentiable Global Positioning". Project page: https://t.co/7PUrmVAn32 (1/5)

[Filippo Aleotti @AleottiFilippo]

DoubleTake is now out! It was a fantastic team effort, directed by the one and only @MohammedAmr1

[Mohamed Sayed @MohammedAmr1]

Are you frustrated of intermittently bad depth maps ruining your online pipeline 😫? Wish you could get fast 🚀 reuse of your previously predicted depth frames? Do you want shiny fast SOTA feedforward depth and meshes ✨?

Introducing DoubleTake!
https://t.co/GvHfIitPLL

[Filippo Aleotti @AleottiFilippo]

We will present AirPlanes tomorrow ✈️ see you at the poster sessions!

[Michael Firman @_mdfirman]

We are excited to present “AirPlanes ✈️: Accurate Plane Estimation via 3D-Consistent Embeddings” at #CVPR2024 in Seattle!

AirPlanes ✈️ gives a lightweight and interpretable 3D planar reconstruction, for AR effects and more! 🤩

https://t.co/A9SnyMgYZF

How do we do this? 👇🧵

[Eric Brachmann @eric_brachmann]

Niantic organises the first #MapFreeReloc workshop and challenge at #ECCV2024 @eccvconf!

We invite the submission of extended abstracts and papers. The challenge features two tracks, and includes a multi-frame version and $6000 in prizes.

Page: https://t.co/FXqVtJpvpo

[Filippo Aleotti @AleottiFilippo]

@MohammedAmr1 @NianticLabs 🎉🎉

[Filippo Aleotti @AleottiFilippo]

Sunday afternoon splats with #Scaniverse ☀️🚀

[Guillermo Garcia-Hernando @gui_ggh]

⚡👋Wave Hello to Hand Tracking! 🙌⚡
I’m excited to share that the hand mesh tracking project I’ve been working on these last months is now live! You can read more about it and try it on your phone and desktop here: https://t.co/nLbLZfX65l 🧵1/4

[Mohamed Sayed @MohammedAmr1]

Were you ever frustrated with jagged edges in AR?! 💔 No more! ✨

📢 Introducing our #CVPR2023 paper (and code!):

Virtual Occlusions Through Implicit Depth❤️🎉

https://t.co/Cnh6oeliYJ
https://t.co/ED4PxrgimW

[1/10]

[Daniyar Turmukhambetov @dantkz]

Niantic is recruiting for Research internship position in London. If you are a PhD student, consider joining us for 3-4 months to work towards a publication.

https://t.co/QkGmBGnfff

[Filippo Aleotti @AleottiFilippo]

@alexk_wong Thank you 🤞🏻

[Filippo Aleotti @AleottiFilippo]

Today is my last day in Bologna 😢 I’m ready to start a new journey in London 🚀

[Filippo Aleotti @AleottiFilippo]

@SattlerTorsten @ducha_aiki Well, maybe not at all the code every time but just at some points if needed! In my case, it helped me to clarify a doubt about how a score was computed

[Filippo Aleotti @AleottiFilippo]

We are live! Join me or @mattpoggi and talk with us about Reversing the Cycle (https://t.co/8G45EWw6nr) and Self-Adaptive Confidence (https://t.co/Kb11YL4DSZ) in our #ECCV2020 poster sessions