Cognitive Computer Vision Lab

We proudly present the static spin illusion - a finalist of the Best Illusion of The Year Contest. You perceive a rotation? There is none! Saleeta Qadir student at @UniFAU built this illusion using computer vision and image processing - please vote for her vote.illusionoftheyear.com

Want to do 2 years of postdoc @CogCoVi @UniFAU in Germany with me? Open Topic around 3D Computer Vision, Neural Rendering, Human Vision, Inverse Rendering, Statistical Shape Modelling or related See the following tweets to see our featured research:

Thrilled to share our work: 𝐀𝐫𝐂𝐒𝐄𝐌: Artistic Colorization of SEM Images via Gaussian Splatting Novel view synthesis of scanning electron microscopy images and Conditional colorization. 📝 arXiv: arxiv.org/abs/2410.21310 🎨Project page: ronly2460.github.io/ArCSEM (1/3)

What are the odds that 5 labs start to work on a very similar story simultaneously? 4 papers on NeRFs with thermal+rgb images released within one week on arXiv! I think this example visualizes the crazy speed of the @CVPR community Now let the Gaussians be splatted...

ArCSEM: Artistic Colorization of SEM Images via Gaussian Splatting Contributions (cited): - We obtain a precise and intricate 3D representation of a pollen captured by Scanning Electron Microscopes (SEM), enabling novel view synthesis. – We achieve 3D colorization of the grayscale 3D scene using a limited number of manually colored images, enabling colored novel view synthesis. – We demonstrate the effectiveness of the proposed approach compared to previous methods through comprehensive experiments.

Very nice work that we presented at @AI4VAECCV24 at @eccvconf ! anyone an idea, when the ECCV workshop proceedings are released?

New PhD position with Tinashe Mutsvangwa and me (2 years @IMTAtlantique, 1 year @UniFAU ) Project Description: imt-atlantique.fr/sites/default/… Application: imt-atlantique.fr/en/research-in…

We had a very inspiring visit of Filip Ilic from TU Graz and Diana Marin from TU Vienna here at VCE @CogCoVi @UniFAU This picuture was taken late in the evening after a very dense schedule filled with science and stories after the biggest BBQ we ever hosted! Thank you both

The Sky’s the Limit: Relightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In Visibility will be at @eccvconf this week! Come check us out at Poster Session 5 #326 for a chat about our work or anything inverse rendering and neural fields!

Today Takuma Nishimura @takuma2460 is presenting ArCSEM: Artistic Colorization of SEM Images via Gaussian Splatting at the AI for visual arts workshop @AI4VAECCV24 #ECCV2024 joint work with @andreead_a and Martin Oeggerli (artist) ronly2460.github.io/ArCSEM/

I'm looking forward to presenting RANRAC: Robust Neural Scene Representations via Random Ray Consensus @eccvconf next week. In a coop of @tudelft & @UniFAU we pushed RANSAC's limits enabling robust neural fields: graphics.tudelft.nl/RANRAC @VisionBernie @ElmarEisemann @andreead_a

It is so nice to see, that the code to generate color inversion illusion we worked on 3 years ago still runs 🥳 Focus on the black dot in the middle for some seconds and you should then perceive a color image for a brief moment x.com/atshubhankar/s…

It is my great honor to have @atshubhankar from @UChicago as our first intern at @CogCoVi at @UniFAU

Very proud to have Frederik Riedmann from @UniFAU presenting his bachelor thesis #CCN2024 @CogCompNeuro joint work with Tim Rohe "Revealing an Unattractivity Bias in Mental Reconstruction of Occluded Faces using Generative Image Models" Paper: 2024.ccneuro.org/pdf/154_Paper_…

Come take a look of my first in-person poster presentation @cogsci_soc from 13:00 - 15:00. PS: Our lab @CogCoVi is looking for 2 postdocs in Human Vision, Computer Vision, Inverse-Rendering or similar open topics!

📢 Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View 🌐 Project page: andreeadogaru.github.io/Gen3DSR 📄 Paper: arxiv.org/abs/2404.03421 👩‍💻 Code: github.com/AndreeaDogaru/… Compositional 3D reconstruction of complex scenes with unprecedented quality🧵

How can we learn a multi-modal neural radiance field? What’s the best way to integrate images from a second modality, other than RGB, into NeRF? Check out our new paper! Project page: mert-o.github.io/ThermalNeRF/ Paper: arxiv.org/abs/2403.11865 Dataset: zenodo.org/records/110658… 1/6

Want to learn more about AI and Art? @lang254 will talk about the history of digital arts and I will make sure you understand how generative AI works! 4. Juli 18:00 in German nuernberg.digital/programm/detai… 4. Juli 20:00 in English nuernberg.digital/programm/detai… @nuedigital @UniFAU

Im Rahmen des Nürnberg Digital Festivals @nuedigital stellen wir unser KI-Experiment an der @UniFAU erneut vor. Mit Vorträgen von @lang254 und mir Donnerstag 4. Juli 18:30 (da ist kein Fussball), Cauerstrasse 11, Erlangen Hier gehts zur Anmeldung: nuernberg.digital/programm/detai…

As part of the Nuremberg Digital Festival @nuedigital we are presenting our AI experiment at @UniFAU for the first time in English! With talsk by @lang254 and me Thursday 4 July 20:00 (there is no soccer), Cauerstrasse 11, Erlangen Click here to register: nuernberg.digital/programm/detai…