Thanks for sharing!
I put care and love into the cover, creating it in QGIS and Illustrator to showcase my beloved Zaragoza
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!
izquierdo.dev/assets/PhD_the…
11
731
Sergio Izquierdo retweeted
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:
civil-software-licenses.gith…
Sergio Izquierdo retweeted
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: nianticspatial.com/blog/cvpr…
MVS Anywhere GitHub: nianticlabs.github.io/mvsany…
Morpheus GitHub: nianticlabs.github.io/morphe…
#CVPR2025 #GeospatialAI #NianticSpatial #ComputerVision #3DMapping #AR #GaussianSplatting #DiffusionModels
Presenting today at #CVPR poster 81.
Code is available at github.com/nianticlabs/mvsan…
Want to try it on an iPhone video? On Android? On any other sequence you have? We got you covered. Check the repo.
🔍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:
nianticlabs.github.io/mvsany…
Happy to be one of them
Behind every great conference is a team of dedicated reviewers. Congratulations to this year’s #CVPR2025 Outstanding Reviewers!
cvpr.thecvf.com/Conferences/…
4
301
🔍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:
nianticlabs.github.io/mvsany…
💡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!
Check the website: nianticlabs.github.io/mvsany…
And the paper: arxiv.org/pdf/2503.22430
Code coming soon!
Great work with @MohammedAmr1 @_mdfirman @gui_ggh @dantkz @jcivera @oisinmacaodha @GBrostow Jamie Watson
Sergio Izquierdo retweeted
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 🤭🤭🤣🤣
Sergio Izquierdo retweeted
ROPERT group from @unizar at @eccvconf #ECCV2024
ropert.i3a.es/
Missing the picture @SeongHunLee1 and José M. M. Montiel
Sergio Izquierdo retweeted
🚀 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.
🔗github.com/amaralibey/OpenVP…
🧵👇
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.
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
arxiv.org/pdf/2407.02422
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.
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.
1
5
215
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:
arxiv.org/abs/2407.02422





















