Michael Weinmann
YOU?
Author Swipe
View article: MKNet-family architectures for auto-segmentation of the residual pancreas after pancreatic resection: a deep learning comparative study
MKNet-family architectures for auto-segmentation of the residual pancreas after pancreatic resection: a deep learning comparative study Open
Purpose Accurate interpretation of CT scans after pancreatic resection is crucial for detecting abnormalities, including postoperative complications and cancer recurrence. This study investigates the feasibility and clinical utility of a n…
View article: SpectralGaussians: Semantic, spectral 3D Gaussian splatting for multi-spectral scene representation, visualization and analysis
SpectralGaussians: Semantic, spectral 3D Gaussian splatting for multi-spectral scene representation, visualization and analysis Open
789
View article: Neural Restoration of Greening Defects in Historical Autochrome Photographs Based on Purely Synthetic Data
Neural Restoration of Greening Defects in Historical Autochrome Photographs Based on Purely Synthetic Data Open
The preservation of early visual arts, particularly color photographs, is challenged by deterioration caused by aging and improper storage, leading to issues like blurring, scratches, color bleeding, and fading defects. Despite great advan…
View article: NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives
NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives Open
While neural radiance fields (NeRF) led to a breakthrough in photorealistic novel view synthesis, handling mirroring surfaces still denotes a particular challenge as they introduce severe inconsistencies in the scene representation. Previo…
View article: Density-based Geometric Convergence of NeRFs at Training Time: Insights from Spatio-temporal Discretization
Density-based Geometric Convergence of NeRFs at Training Time: Insights from Spatio-temporal Discretization Open
Whereas emerging learning-based scene representations are predominantly evaluated based on image quality metrics such as PSNR, SSIM or LPIPS, only a few investigations focus on the evaluation of geometric accuracy of the underlying model. …
View article: DeepMaterialInsights: A Web-based Framework Harnessing Deep Learning for Estimation, Visualization, and Export of Material Assets from Images
DeepMaterialInsights: A Web-based Framework Harnessing Deep Learning for Estimation, Visualization, and Export of Material Assets from Images Open
Accurately replicating the appearance of real-world materials in computer graphics is a complex task due to the intricate interactions between light, reflectance, and geometry. In this paper we address the challenges of material representa…
View article: SpectralSplatsViewer: An Interactive Web-Based Tool for Visualizing Cross-Spectral Gaussian Splats
SpectralSplatsViewer: An Interactive Web-Based Tool for Visualizing Cross-Spectral Gaussian Splats Open
Spectral rendering accurately simulates light-material interactions by considering the entire light spectrum, unlike traditional rendering methods that use limited color channels like RGB. This technique is particularly valuable in industr…
View article: SpectralGaussians: Semantic, spectral 3D Gaussian splatting for multi-spectral scene representation, visualization and analysis
SpectralGaussians: Semantic, spectral 3D Gaussian splatting for multi-spectral scene representation, visualization and analysis Open
We propose a novel cross-spectral rendering framework based on 3D Gaussian Splatting (3DGS) that generates realistic and semantically meaningful splats from registered multi-view spectrum and segmentation maps. This extension enhances the …
View article: The Potential of Neural Radiance Fields and 3D Gaussian Splatting for 3D Reconstruction from Aerial Imagery
The Potential of Neural Radiance Fields and 3D Gaussian Splatting for 3D Reconstruction from Aerial Imagery Open
In this paper, we focus on investigating the potential of advanced Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting for 3D scene reconstruction from aerial imagery obtained via sensor platforms with an almost nadir-looking camera. …
View article: Incomplete Gamma Kernels: Generalizing Locally Optimal Projection Operators
Incomplete Gamma Kernels: Generalizing Locally Optimal Projection Operators Open
We present incomplete gamma kernels, a generalization of Locally Optimal Projection (LOP) operators. In particular, we reveal the relation of the classical localized L1 estimator, used in the LOP operator for point cloud denoising, to the …
View article: Neural inverse procedural modeling of knitting yarns from images
Neural inverse procedural modeling of knitting yarns from images Open
We investigate the capabilities of neural inverse procedural modeling to infer high-quality procedural yarn models with fiber-level details from single images of depicted yarn samples. While directly inferring all parameters of the underly…
View article: RANRAC: Robust Neural Scene Representations via Random Ray Consensus
RANRAC: Robust Neural Scene Representations via Random Ray Consensus Open
Learning-based scene representations such as neural radiance fields or light field networks, that rely on fitting a scene model to image observations, commonly encounter challenges in the presence of inconsistencies within the images cause…
View article: Neural inverse procedural modeling of knitting yarns from images
Neural inverse procedural modeling of knitting yarns from images Open
We investigate the capabilities of neural inverse procedural modeling to infer high-quality procedural yarn models with fiber-level details from single images of depicted yarn samples. While directly inferring all parameters of the underly…
View article: Efficient 3D Reconstruction, Streaming and Visualization of Static and Dynamic Scene Parts for Multi-client Live-telepresence in Large-scale Environments
Efficient 3D Reconstruction, Streaming and Visualization of Static and Dynamic Scene Parts for Multi-client Live-telepresence in Large-scale Environments Open
Despite the impressive progress of telepresence systems for room-scale scenes with static and dynamic scene entities, expanding their capabilities to scenarios with larger dynamic environments beyond a fixed size of a few square-meters rem…
View article: BoundED: Neural Boundary and Edge Detection in 3D Point Clouds via Local Neighborhood Statistics
BoundED: Neural Boundary and Edge Detection in 3D Point Clouds via Local Neighborhood Statistics Open
Extracting high-level structural information from 3D point clouds is challenging but essential for tasks like urban planning or autonomous driving requiring an advanced understanding of the scene at hand. Existing approaches are still not …
View article: Locally-guided neural denoising
Locally-guided neural denoising Open
Noise-like artifacts are common in measured or fitted data across various domains, e.g. photography, geometric reconstructions in terms of point clouds or meshes, as well as reflectance measurements and the respective fitting of commonly u…
View article: Spline-PINN: Approaching PDEs without Data Using Fast, Physics-Informed Hermite-Spline CNNs
Spline-PINN: Approaching PDEs without Data Using Fast, Physics-Informed Hermite-Spline CNNs Open
Partial Differential Equations (PDEs) are notoriously difficult to solve. In general, closed form solutions are not available and numerical approximation schemes are computationally expensive. In this paper, we propose to approach the solu…
View article: FaDIV-Syn: Fast Depth-Independent View Synthesis using Soft Masks and Implicit Blending
FaDIV-Syn: Fast Depth-Independent View Synthesis using Soft Masks and Implicit Blending Open
Novel view synthesis is required in many robotic applications, such as VR teleoperation and scene reconstruction.Existing methods are often too slow for these contexts, cannot handle dynamic scenes, and are limited by their explicit depth …
View article: Incomplete Gamma Kernels: Generalizing Locally Optimal Projection Operators
Incomplete Gamma Kernels: Generalizing Locally Optimal Projection Operators Open
We present incomplete gamma kernels, a generalization of Locally Optimal Projection (LOP) operators. In particular, we reveal the relation of the classical localized $ L_1 $ estimator, used in the LOP operator for point cloud denoising, to…
View article: Occlusion Fields: An Implicit Representation for Non-Line-of-Sight Surface Reconstruction
Occlusion Fields: An Implicit Representation for Non-Line-of-Sight Surface Reconstruction Open
Non-line-of-sight reconstruction (NLoS) is a novel indirect imaging modality that aims to recover objects or scene parts outside the field of view from measurements of light that is indirectly scattered off a directly visible, diffuse wall…
View article: Towards Tangible Cultural Heritage Experiences—Enriching VR-based Object Inspection with Haptic Feedback
Towards Tangible Cultural Heritage Experiences—Enriching VR-based Object Inspection with Haptic Feedback Open
VR/AR technology is a key enabler for new ways of immersively experiencing cultural heritage artifacts based on their virtual counterparts obtained from a digitization process. In this article, we focus on enriching VR-based object inspect…
View article: Weakly-Supervised Single-view Dense 3D Point Cloud Reconstruction via Differentiable Renderer
Weakly-Supervised Single-view Dense 3D Point Cloud Reconstruction via Differentiable Renderer Open
In recent years, addressing ill-posed problems by leveraging prior knowledge contained in databases on learning techniques has gained much attention. In this paper, we focus on complete three-dimensional (3D) point cloud reconstruction bas…
View article: Spline-PINN: Approaching PDEs without Data using Fast, Physics-Informed Hermite-Spline CNNs
Spline-PINN: Approaching PDEs without Data using Fast, Physics-Informed Hermite-Spline CNNs Open
Partial Differential Equations (PDEs) are notoriously difficult to solve. In general, closed-form solutions are not available and numerical approximation schemes are computationally expensive. In this paper, we propose to approach the solu…
View article: FaDIV-Syn: Fast Depth-Independent View Synthesis using Soft Masks and Implicit Blending
FaDIV-Syn: Fast Depth-Independent View Synthesis using Soft Masks and Implicit Blending Open
Novel view synthesis is required in many robotic applications, such as VR teleoperation and scene reconstruction. Existing methods are often too slow for these contexts, cannot handle dynamic scenes, and are limited by their explicit depth…
View article: FaDIV-Syn: Fast Depth-Independent View Synthesis.
FaDIV-Syn: Fast Depth-Independent View Synthesis. Open
We introduce FaDIV-Syn, a fast depth-independent view synthesis method. Our multi-view approach addresses the problem that view synthesis methods are often limited by their depth estimation stage, where incorrect depth predictions can lead…
View article: KNOWLEDGE AND SKILLS RELATED TO ACTIVE OPTICAL SENSORS IN THE BODY OF KNOWLEDGE FOR EARTH OBSERVATION AND GEOINFORMATION (EO4GEO BOK)
KNOWLEDGE AND SKILLS RELATED TO ACTIVE OPTICAL SENSORS IN THE BODY OF KNOWLEDGE FOR EARTH OBSERVATION AND GEOINFORMATION (EO4GEO BOK) Open
The field of Earth Observation (EO) and Geoinformation (GI) is gaining more and more importance due to the increasing number of data and data processing algorithms to respond even more accurately to a variety of challenges in many applicat…
View article: Fast Fluid Simulations in 3D with Physics-Informed Deep Learning.
Fast Fluid Simulations in 3D with Physics-Informed Deep Learning. Open
Physically plausible fluid simulations play an important role in modern computer graphics. However, in order to achieve real-time performance, computational speed needs to be traded-off with physical accuracy. Surrogate fluid models based …