Sergio Izquierdo

PhD student in computer vision at University of Zaragoza

[Sergio Izquierdo @serizba]

Thanks for sharing!

I put care and love into the cover, creating it in QGIS and Illustrator to showcase my beloved Zaragoza

[Dmytro Mishkin 🇺🇦 @ducha_aiki]

Deep Spatial Perception:
Localization & Reconstruction.

PhD thesis of @serizba
tl;dr: mostly papers combined, but they are good (e.g. DINO-SALAD) and look at the gorgeous title page!
https://t.co/qD7EdQe8pB

[Bernhard Jaeger @bern_jaeger]

One concern that I have as an AI researcher when publishing code is that it can potentially be used in dual-use applications.
To solve this, we propose Civil Software Licenses. They prevent dual-use while being minimal in the restrictions they impose:

https://t.co/gikJHAAMkd

[Niantic Spatial 🌎 @NianticSpatial]

This week at #CVPR2025, Niantic Spatial is sharing the major strides made toward building a Large Geospatial Model that merges the digital and physical worlds. 🌍🧠

📐MVSAnywhere: Zero-Shot Multi-View Stereo

🎨 Morpheus: Generative 3D Scene Stylization
These two research projects reflect a larger ambition: to make AI systems that are spatially aware – able to perceive, interpret, and understand the physical world.

🔗See full blog and GitHub links:

Blog post: https://t.co/JrQBkd9AYl
MVS Anywhere GitHub: https://t.co/mAiuLvciPj
Morpheus GitHub: https://t.co/ulBZMB9tRF

#CVPR2025 #GeospatialAI #NianticSpatial #ComputerVision #3DMapping #AR #GaussianSplatting #DiffusionModels

[Sergio Izquierdo @serizba]

Presenting today at #CVPR poster 81.

Code is available at https://t.co/c8uNbU2L5C

Want to try it on an iPhone video? On Android? On any other sequence you have? We got you covered. Check the repo.

[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

[Sergio Izquierdo @serizba]

Happy to be one of them

[#CVPR2026 @CVPR]

Behind every great conference is a team of dedicated reviewers. Congratulations to this year’s #CVPR2025 Outstanding Reviewers!

https://t.co/z8w4YJKTep

[Sergio Izquierdo @serizba]

Check the website: https://t.co/sH1wsbXTkB
And the paper: https://t.co/sLV5ml1wv9
Code coming soon!

Great work with @MohammedAmr1 @_mdfirman @gui_ggh @dantkz @jcivera @oisinmacaodha   @GBrostow Jamie Watson

[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

[Sergio Izquierdo @serizba]

💡Use case:

We show how the accurate and robust depths from MVSAnywhere serve to regularize gaussian splats, obtaining much cleaner scene reconstructions.

As MVSAnywhere is agnostic to the scene scale, this is plug-and-play for your splats!

[Javier Civera @jcivera]

Just today, I evaluated our #ECCV2024 work in an additional downstream task as a table cloth. It performed similarly to commercial baselines without task-specific fine tuning 🤭🤭🤣🤣

[Dmytro Mishkin 🇺🇦 @ducha_aiki]

Geographical mining to improve dinosalad
#ECCV2024 @serizba
@jcivera
https://t.co/XyksDyCyoq

[Sergio Izquierdo @serizba]

Do you want to boost the performance of your Visual Place Recognition model? Check our poster 260 at #ECCV2024 and discover how an effective mining strategy can boost it's sensitivity. With @jcivera

[Ruben Martinez-Cantin @rmcantin]

ROPERT group from @unizar at @eccvconf #ECCV2024

https://t.co/2C0hpTZFwA

Missing the picture @SeongHunLee1 and José M. M. Montiel

[Amar Ali-bey @amaralibey]

🚀 Excited to release OpenVPRLab! 🎉
An open-source framework for Visual Place Recognition (VPR), featuring extensible, modular, and scalable components, enabling researchers to train/develop deep VPR models with reproducible SOTA performance.

🔗https://t.co/2pWkiGwzIq

🧵👇

[Sergio Izquierdo @serizba]

Just accepted to #ECCV2024

We analyse and describe the Geographic Distance Sensitivity and propose a mining strategy to boost it, greatly improving performance on Visual Place Recognition.

[Zhenjun Zhao @zhenjun_zhao]

Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition

@serizba, @jcivera

tl;dr: analyze Geographic Distance Sensitivity (GDS) of VPR embeddings; training samples->graph->extract cliques->geographically close images

https://t.co/ppwoRMQXaL

[Sergio Izquierdo @serizba]

We propose a novel mining strategy, CliqueMining, which creates very difficult batches of very similar images. This boost the Geographic Distance Sensitivity of the models, increasing recalls by a very big margin. With @jcivera.

Check the paper:
https://t.co/9mpuMqyQd7

[Sergio Izquierdo @serizba]

Some recent works on VPR work very well. However, in our just accepted #ECCV2024 paper we identified a common failure case where retrieved images are close, but above the positive threshold.

[Sergio Izquierdo @serizba]

In our paper, "Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition", we analysed how some models fail to correctly rank relatively close frames. This drastically lowers the obtained recalls.