Maximilian Weiherer
@maxweiherer
Followers
153
Following
1K
Media
23
Statuses
177
PhD student @UniFAU. Part of @CogCoVi. I’m working at the intersection of computer vision, computer graphics, and machine learning. I like kernels.
Joined December 2021
(4/4) Great work led by Josef Grün & Lukas Meyer and with @maxweiherer, @VisionBernie, Marc Stamminger, and @_linus_franke! 📄Paper: https://t.co/26fyjKiCSU 📷Code: https://t.co/tTFJdj7ImT
#VMV25 #GaussianSplatting #NeRF #Multispectral #Rendering
github.com
Multi-Spectral Gaussian Splatting with Neural Color Representation - j-gruen/MS-Splatting
0
0
1
Towards Integrating Multi-Spectral Imaging with Gaussian Splatting Contributions: • Formulation and comparison of multi-spectral integration strategies: We introduce and systematically evaluate three optimization paradigms—SEPARATE, SPLIT, and JOINT—for incorporating additional
3
9
100
(3/4) 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.
1
0
1
(2/4) While 3D Gaussian Splatting (3DGS) excels on RGB data, naive per-band optimization of additional spectra yields poor reconstructions due to inconsistently appearing geometry in the spectral domain.
1
0
1
🚀Excited to share our paper "Towards Integrating Multi-Spectral Imaging with Gaussian Splatting" was accepted at VMV 2025! 🎉 We fuse RGB & multi-spectral imagery (red, green, red-edge, near-infrared) into the 3D Gaussian Splatting framework. 🔗Project: https://t.co/qwEQfA1V7G
1
5
50
NeurIPS is pleased to officially endorse EurIPS, an independently-organized meeting taking place in Copenhagen this year, which will offer researchers an opportunity to additionally present their accepted NeurIPS work in Europe, concurrently with NeurIPS. Read more in our blog
10
122
805
(5/5) Huge thanks to my co-authors, Antonia von Riedheim, Vanessa Brébant, @VisionBernie, and Christoph Palm.
0
0
1
(4/5) The resulting model is free of correspondence errors, captures detailed surface geometry, and outperforms the RBSM in various surface reconstruction tasks. The iRBSM is publicly available for research purposes! Model: https://t.co/lmZYGlSTWT Code: https://t.co/4kH6qLq36G
1
0
0
(3/5) Using an implicit (correspondence-free) representation to model breast shapes from surface-only 3D scans is highly advantageous, as registering these scans is extremely hard: almost no features, large deformations, and severe occlusions (esp. underbust).
1
0
1
(2/5) Our model uses a DeepSDF architecture and is trained directly on 168 raw 3D breast scans--without ground truth supervision. Contrary to the RBSM, no surface registration is required to bring training data into correspondence.
1
0
1
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: https://t.co/gQU1mnBLF3
1
3
11
Huge progress by @artuursberzins @AndyRadler @e_volkmann on Geometry-Informed Neural Networks (GINNs)! Faster training, better shapes, and surprising insights from enforcing diversity. 📜: https://t.co/hI3FdgCDeC 🖥️: https://t.co/qRbJ9SWWms
We introduce Geometry-Informed Neural Networks to train shape generative models without any data (!!), combining learning under constraints, neural fields as a suitable representation, and generating diverse solutions to under-determined problems: 🖥️: https://t.co/qRbJ9SXuc0
2
31
212
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...
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: https://t.co/m7lguL94dp Paper: https://t.co/449gwU5viS Dataset: https://t.co/uOvWykg509 1/6
2
4
43
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: https://t.co/jLKmDLARUo 🎨Project page: https://t.co/twRqvQozL0 (1/3)
5
14
35
🚨🚨🚨🚨🚨 Paper Alert 🚨🚨🚨🚨🚨 NeRFtrinsic Four: An End-To-End Trainable NeRF Jointly Optimizing Diverse Intrinsic and Extrinsic Camera Parameters has been accepted to #CVIU!!! (1/4)
5
3
7
❓️Want to fuse RGB-D 📷 with high-resolution radars 📡 ? ➡️ Check out our paper "Automatic Spatial Calibration of Near-Field MIMO Radar With Respect to Optical Depth Sensors" 🤖 Accepted at #iros 2024 🌐: https://t.co/kFCqHNORbQ 📃: https://t.co/Ha1cVbDzJE
0
4
8
First time at #ECCV, with two interesting main conference days already behind us. Today afternoon, Mathias Öttl is presenting his paper on "Style-Extracting Diffusion Models for Semi-Supervised Histopathology Segmentation" - join us at Poster #342! 🔬 https://t.co/1GSRXN2K6V
0
4
22
