iiinova — where your digital self keeps evolving

Lukas Meyer

@meyels.bsky.social

Ph.D. student @FAU.de - LGDV / LIKE | Computer Vision 🤖| Digital Horticulture 🌳🍒 meyerls.github.io

Lukas Meyer @meyels.bsky.social · 03/09/2025

Great work led by Josef Grün & Lukas Meyer and with @maxweiherer.bsky.social, @visionbernie.bsky.social, @mcstammi.bsky.social and @linusfranke.bsky.social!

000

Lukas Meyer @meyels.bsky.social · 03/09/2025

To explore this, we systematically compare three strategies for incorporating multi-spectral data into 3DGS and show how spectral cross-talk (the exchange of information between RGB and multi-spectral data) enhances both RGB and spectral reconstructions.

100

Lukas Meyer @meyels.bsky.social · 03/09/2025

While 3DGS excels on RGB data, naive per-band optimization of additional spectra yields poor reconstructions due to inconsistently appearing geometry in the spectral domain.

100

Lukas Meyer @meyels.bsky.social · 03/09/2025

We fuse RGB and multi-spectral imagery (red, green, red-edge, near-infrared) into the 3D Gaussian Splatting (3DGS) framework.

100

Lukas Meyer @meyels.bsky.social · 03/09/2025

🚀 Excited to share that our paper "Towards Integrating Multi-Spectral Imaging with Gaussian Splatting" was accepted at VMV 2025! 🎉 🔗 Project: meyerls.github.io/towards_mult... 📄 Paper: arxiv.org/pdf/2509.00989 💻 Code: github.com/j-gruen/MS-S... #VMV25 #GaussianSplatting #NeRF #Multispectral

173

Reposted by Lukas Meyer

VisionBernie - Bernhard Egger @visionbernie.bsky.social · 12/11/2024

Want to do 2 years of postdoc @cogcovi.bsky.social @unifau.bsky.social in Germany with me? Open Topic around 3D Computer Vision, Neural Rendering, Human Vision, Inverse Rendering, Statistical Shape Modelling or related

0166

Reposted by Lukas Meyer

Maximilian Weiherer @maxweiherer.bsky.social · 19/12/2024

Happy to share our latest 3D generative breast model: the *implicit* RBSM, or iRBSM for short. As opposed to its PCA-based predecessor, the iRBSM leverages implicit neural representations, yielding a highly detailed and expressive 3D breast model. Paper: arxiv.org/abs/2412.13244

1103