iiinova — where your digital self keeps evolving

Reposted by Andreea Ardelean

VisionBernie - Bernhard Egger @visionbernie.bsky.social · 01/10/2026

We are recruiting an ELLIS PhD student (100% E13) at FAU Germany for a joint ANR-DFG project with Sarah Matta and Tinashe Mutsvangwa from IMT Atlantique. Apply via the ELLIS PhD program: ellis.eu/news/ellis-p... Image generated by Gemini (1/3)

153

Reposted by Andreea Ardelean

VisionBernie - Bernhard Egger @visionbernie.bsky.social · 21/02/2026

Very proud of Paul who got his master thesis at @fau.de accepted at @cvprconference.bsky.social - the most impactful conference! Joint supervision with @andreead-a.bsky.social , @jadgardner.bsky.social and @willsmithvision.bsky.social

073

Reposted by Andreea Ardelean

tardelean.bsky.social @tardelean.bsky.social · 05/02/2026

At SIGGRAPH Asia in December, I presented our latest work on generating arbitrarily large, tileable textures with irregular features, developed together with @timweyrich.bsky.social. 🎨 Today I am excited to announce we added a Blender plugin to our official code release: github.com/TArdelean/Fe... 😄

122

Andreea Ardelean @andreead-a.bsky.social · 26/03/2025

Had a great experience presenting our work on 3D scene reconstruction from a single image with @visionbernie.bsky.social at #3DV2025 🇸🇬 andreeadogaru.github.io/Gen3DSR Reach out if you're interested in discussing our research or exploring international postdoc opportunities @fau.de

0184

Reposted by Andreea Ardelean

FAU Erlangen-Nbg @fau.de · 29/11/2024

Scanning Electron Microscopes analyze invisible surfaces. However, they’re only able to take grayscale images. Manual coloring is a cumbersome process and that’s why FAU researchers are using the 3D structure to propagate one colorized view to a whole scene. Impressive! 🎨 Artwork by Micronaut.

1214

Andreea Ardelean @andreead-a.bsky.social · 19/11/2024

Work with @mert-o.bsky.social and @visionbernie.bsky.social at @cogcovi.bsky.social @unifau.bsky.social, where we have two year fully-funded postdoc positions open on related topics. (5/5)

040

Andreea Ardelean @andreead-a.bsky.social · 19/11/2024

We handle occlusions by employing amodal completion for each instance. The completed instance is then reconstructed using existing models that perform well for single objects. However, we first address the object crop domain shift (e.g., focal length) through reprojection. (4/5)

131

Andreea Ardelean @andreead-a.bsky.social · 19/11/2024

First, we parse the image of the scene by identifying the composing entities and estimating the depth and camera parameters. Each instance is then processed individually. The unprojected depth serves as a layout reference for composing the scene in 3D space. (3/5)

131

Andreea Ardelean @andreead-a.bsky.social · 19/11/2024

Most single-image scene-level reconstruction methods require 3D supervised end-to-end training and suffer from poor generalization capabilities. We propose a modular approach where each component performs well by focusing on specific tasks that are easier to supervise. (2/5)

121

Andreea Ardelean @andreead-a.bsky.social · 19/11/2024

Excited to share our paper which will be presented at #3DV2025 ✨ 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/AndreeaDogar... (1/5)

1236