(1/5) Thrilled to present “H3D-Net”, a method for reconstructing high-fidelity human heads in 3D from small sets of images. This is joint work with Gil Triginer Garces, Janna Escur, Albert Pumarola, Jaime Garcia, Xavi Giró, and Francesc Moreno-Noguer. Project page: crisalixsa.github.io/h3d-net

Today is Deep Learning Barcelona Symposium 2022 ! If you cannot make it to Campus Norr UPC, watch it on YouTube starting 9am CET with the keynote of Laura Leal-Taixé. #DLBCN youtu.be/kD7KN4apFEk

Welcome to the official account of Crisalix Labs, where we will share exciting research!

We love to see the H3Ds dataset being used in great research!

Pol Casellas (Pol Caselles) from Crisalix kicks off the 3D session for full head reconstruction from a single image. #WACV2023 #DLBCN arxiv.org/abs/2209.03027

Great work on single view reconstruction and relighting by Pol Caselles !

Proud to sponsor the Deep Learning Barcelona Symposium again this year! Looking forward to catching up with the hugely talented community of DL researchers in/from Barcelona. Come by our stand to say hi and meet our team. We’ll also have some cool demos!

We have just released the H3DS 2.0 dataset with up to 59 scenes 🎉🎉. Both the data and the evaluation code are accesible through a Python package. You can start using it at github.com/CrisalixSA/h3ds

👋 Hello European Conference on Computer Vision #ECCV2026 ! Crisalix is attending #ECCV2024, if you see Ibrar Malik Pol Caselles marcelo Sanchez and want to talk 3D / CV, come say hi.

It has been a great experience to attend 3DBODY.TECH ! We enjoyed seeing the latest innovations in the field and sharing what we’ve been up to.

Crisalix (CrisalixLabs) will be a gold sponsor of the Deep Learning Barcelona Symposium 2024. Crisalix was already a sponsor in the first edition of #DLBCN back in 2018. crisalix.com/en

Another year, another #DLBCN symposium we are attending. Proud to support the Barcelona deep learning community and meet all the researchers today!

(1/3) 📢Excited to share that our journal paper "Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstruction" has been accepted to #IEEE Transactions on Pattern Analysis and Machine Intelligence (#TPAMI) 🔗Project: crisalixsa.github.io/sira-plus-plus/

[1/3] I am thrilled to announce that RETHINED: Real-Time High Resolution Image Inpainting On Edge Devices is being presented as an Oral today at #WACV2025! 📅Oral Session 5.4: Generative Models V 14:00 project: crisalixsa.github.io/rethined/

[1/2]📢 Excited to share that our paper "GLVD: Guided Learned Vertex Descent" has been accepted to #NeurIPS 2025! 🎉 Check them out here: 🔗 Paper: arxiv.org/pdf/2510.06046 🔗 Project: crisalixsa.github.io/glvd/ This is a joint collaboration with Francesc Moreno Noguer.