Iago Suárez

📢I'm pleased to introduce GlueStick: A robust image matcher that combines points and lines📢 ➡️Website: iago-suarez.com/gluestick ➡️Code: github.com/cvg/GlueStick ➡️Paper: arxiv.org/pdf/2304.02008… This is a collaboration with Rémi Pautrat, Yifan Yu, @mapo1 and @visionviktor. 1/🧵

One of the more interesting and thought provoking research papers I've seen in a while. A system for reading and reimplementing NeRF papers, and it seems to work very well. Pretty easy to extrapolate out from here to what CVPR 2027 papers will look like. seemandhar.github.io/NERFIFY/

We can now 3dfy any object from a single real world image. This has been a holy grail in computer vision for many decades. Try it here (you can upload your own images) aidemos.meta.com/segment-anythi… and you can read the paper here ai.meta.com/.../sam-3d-3df… . Enjoy!

Aidyn Ubingazhibov 1 Rémi Pautrat 2 @IagoSuarez0 3 @B1ueber2y 1 @mapo1 1,2 @visionviktor 1 @ETH_en 2 @Microsoft 3 @Qualcomm 4 @lunduniversity Paper: arxiv.org/pdf/2510.16438 Project page: github.com/aubingazhib/Li… (apache 2 but non commercial due to SuperPoint)

LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching Aidyn Ubingazhibov, Rémi Pautrat, @IagoSuarez0, @B1ueber2y, @mapo1, @visionviktor tl;dr: LightGlue+GlueStick+line message arxiv.org/abs/2510.16438

LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching Aidyn Ubingazhibov, Rémi Pautrat, Iago Suárez, @B1ueber2y , @mapo1 @visionviktor tl;dr: Better and faster gluestick with line attention. arxiv.org/abs/2510.16438

@ducha_aiki @olafbrandt Very cool paper! I imagine a lot of applications in eXtended Reality to remove furniture or architecture re-design, so called diminished reality 💡🚀

An Empty Room is All We Want: Automatic Defurnishing of Indoor Panoramas Mira Slavcheva, Dave Gausebeck, Kevin Chen, David Buchhofer, Azwad Sabik, Chen Ma, Sachal Dhillon, @olafbrandt, Alan Dolhasz tl;dr: train on synthetic furniture on real empty photos arxiv.org/abs/2405.03682

Congrats to all my friends in @wayve_ai , this is a huge achievement 🔥🥳

Very cool day in @usingstdcpp talking about the cool things we do at @Qualcomm 🥽🔥

I just find this paper extremely cool! 😎 Actually, there's a very interesting overlap between this and GlueStick, because if both techniques were combined, it would be very easy to get low-poly meshes of the objects in the scene 🤔

🏆 3DV 2024 Best Paper Award, Honorable Mention! 🏆 Congratulations!!

On #InternationalWomensDay, I am feeling immense pride in the culture we've built at @Waabi_ai . Here's to all the incredible women of Waabi and the world who inspire me daily.

Interested in computer vision/ML/math/geometry? Open PhD positions available in my group, more details at vlarsson.github.io/positions/

Mañana miércoles 31 de enero @IagoSuarez0 participa en los seminarios del @VisionArtif con la conferencia "Image matching" en el salón de grados del Departamental 2 del campus de Móstoles de la URJC (18:00). Más información en mastervisionartificial.es/event/image-ma…

@ducha_aiki Any insight on why poselib gets better results using SP+LG instead of ALIKED+LG for MegaDepth?

Short guide for modern local features: - if you are GPU and CPU-rich, use RoMA - if you are allergic to learned matching, use DeDoDe. - otherwise use ALIKED+LightGlue.

Segment3D explores the use of 2D foundation models to automatically generate training labels for 3D segmentation. It predicts accurate segmentation masks, improves over fully-supervised 3D segmentation methods e.g., Mask3D, and requires no manually labeled 3D training data. Segment3D is a method for class-agnostic 3D scene segmentation that produces high-quality 3D segmentation masks, improves over existing 3D segmentation models (especially on fine-grained masks), and enables easily adding new training data to further boost the segmentation performance - all without the need for manual labels. Paper: Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels by Rui Huang @songyoupeng and team Link: arxiv.org/abs/2312.17232 Project: segment3d.github.io #3D #deeplearning #AIイラスト #AI美女 #AI

@dancasas This project is very cool! 😎

We are finally rolling out the SMPLitex dataset and text-to-texture generative model. If you are working with SMPL and require photorealistc textures, SMPLitex will to do it for you! I hope it's useful for rendering and training data-driven methods 🙂 github.com/dancasas/SMPLi…

Congrats Dr. Peng @songyoupeng 🥳🎉 I am very proud of having a friend like you. You just did an incredible PhD!

📢 ¡Vuelve #MadridMLMeetup! Un encuentro para compartir los avanzes en #MachineLearning. 🗓️ 25/10 ⌚ 18:30 h Con Iago Suárez, de @Qualcomm XR Labs Europe; exploraremos la tecnología de #ImageMatching, fundamental en #VisiónArtificial! 👁️🚀 🚩Registro 👉 lnkd.in/dsuQs_pi

@DRozumnyi This paper is very cool Denys! Congratulations 🎉🥳

My internship work at Google got accepted to NeurIPS!

💣We are releasing the training code for GlueStick in a joint effort with our friends from LightGlue! With glue-factory you can train a matcher with any kind of feature, use different robust estimators, and evaluate in several benchmarks: ✅github.com/cvg/glue-facto…