output
20022026
most citedMethods for Interpreting and Understanding Deep Neural Networks

2.8k citations

Showing cs.CVShow all

39 papers · 1 filter

cs.CV2025

SPNeRF: Open Vocabulary 3D Neural Scene Segmentation with Superpoints

Weiwen Hu, Niccolò Parodi, Marcus Zepp +3

Open-vocabulary segmentation, powered by large visual-language models like CLIP, has expanded 2D segmentation capabilities beyond fixed classes predefined by the dataset, enabling…

cs.CV2025★ 4 cited

Improving Adaptive Density Control for 3D Gaussian Splatting

Glenn Grubert, Florian Barthel, Anna Hilsmann +1

3D Gaussian Splatting (3DGS) has become one of the most influential works in the past year. Due to its efficient and high-quality novel view synthesis capabilities, it has been wid…

cs.CV2025

Improving Geometric Consistency for 360-Degree Neural Radiance Fields in Indoor Scenarios

Iryna Repinetska, Anna Hilsmann, Peter Eisert

Photo-realistic rendering and novel view synthesis play a crucial role in human-computer interaction tasks, from gaming to path planning. Neural Radiance Fields (NeRFs) model scene…

cs.CV2025

Automatic Drywall Analysis for Progress Tracking and Quality Control in Construction

Mariusz Trzeciakiewicz, Aleixo Cambeiro Barreiro, Niklas Gard +2

Digitalization in the construction industry has become essential, enabling centralized, easy access to all relevant information of a building. Automated systems can facilitate the…

cs.CV2025★ 2 cited

Creating Sorted Grid Layouts with Gradient-based Optimization

Kai Uwe Barthel, Florian Tim Barthel, Peter Eisert +2

Visually sorted grid layouts provide an efficient method for organizing high-dimensional vectors in two-dimensional space by aligning spatial proximity with similarity relationship…

cs.CV2024★ 1 cited

Multi-Resolution Generative Modeling of Human Motion from Limited Data

David Eduardo Moreno-Villamarín, Anna Hilsmann, Peter Eisert

We present a generative model that learns to synthesize human motion from limited training sequences. Our framework provides conditional generation and blending across multiple tem…

cs.CV2024★ 36 cited

3DGS.zip: A survey on 3D Gaussian Splatting Compression Methods

Milena T. Bagdasarian, Paul Knoll, Yi-Hsin Li +4

3D Gaussian Splatting (3DGS) has emerged as a cutting-edge technique for real-time radiance field rendering, offering state-of-the-art performance in terms of both quality and spee…

cs.CV2024★ 4 cited

Explainable concept mappings of MRI: Revealing the mechanisms underlying deep learning-based brain disease classification

Christian Tinauer, Anna Damulina, Maximilian Sackl +9

Motivation. While recent studies show high accuracy in the classification of Alzheimer's disease using deep neural networks, the underlying learned concepts have not been investiga…

cs.CV2024★ 12 cited

Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networks

Florian Barthel, Arian Beckmann, Wieland Morgenstern +2

NeRF-based 3D-aware Generative Adversarial Networks (GANs) like EG3D or GIRAFFE have shown very high rendering quality under large representational variety. However, rendering with…

cs.CV2024★ 4 cited

SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen Environments

Niklas Gard, Anna Hilsmann, Peter Eisert

In this paper, we present SPVLoc, a global indoor localization method that accurately determines the six-dimensional (6D) camera pose of a query image and requires minimal scene-sp…

cs.CV2024★ 3 cited

Video-Driven Animation of Neural Head Avatars

Wolfgang Paier, Paul Hinzer, Anna Hilsmann +1

We present a new approach for video-driven animation of high-quality neural 3D head models, addressing the challenge of person-independent animation from video input. Typically, hi…

cs.CV2024★ 8 cited

X-maps: Direct Depth Lookup for Event-based Structured Light Systems

Wieland Morgenstern, Niklas Gard, Simon Baumann +2

We present a new approach to direct depth estimation for Spatial Augmented Reality (SAR) applications using event cameras. These dynamic vision sensors are a great fit to be paired…

cs.CV2023★ 80 cited

Compact 3D Scene Representation via Self-Organizing Gaussian Grids

Wieland Morgenstern, Florian Barthel, Anna Hilsmann +1

3D Gaussian Splatting has recently emerged as a highly promising technique for modeling of static 3D scenes. In contrast to Neural Radiance Fields, it utilizes efficient rasterizat…

cs.CV2023★ 2 cited

Animating NeRFs from Texture Space: A Framework for Pose-Dependent Rendering of Human Performances

Paul Knoll, Wieland Morgenstern, Anna Hilsmann +1

Creating high-quality controllable 3D human models from multi-view RGB videos poses a significant challenge. Neural radiance fields (NeRFs) have demonstrated remarkable quality in…

cs.CV2023★ 6 cited

Animatable Virtual Humans: Learning pose-dependent human representations in UV space for interactive performance synthesis

Wieland Morgenstern, Milena T. Bagdasarian, Anna Hilsmann +1

We propose a novel representation of virtual humans for highly realistic real-time animation and rendering in 3D applications. We learn pose dependent appearance and geometry from…

cs.CV2023★ 21 cited

Automatic Reconstruction of Semantic 3D Models from 2D Floor Plans

Aleixo Cambeiro Barreiro, Mariusz Trzeciakiewicz, Anna Hilsmann +1

Digitalization of existing buildings and the creation of 3D BIM models for them has become crucial for many tasks. Of particular importance are floor plans, which contain informati…

cs.CV2023★ 1 cited

System for 3D Acquisition and 3D Reconstruction using Structured Light for Sewer Line Inspection

Johannes Künzel, Darko Vehar, Rico Nestler +3

The assessment of sewer pipe systems is a highly important, but at the same time cumbersome and error-prone task. We introduce an innovative system based on single-shot structured…

cs.CV2022★ 11 cited

Hyperspectral Demosaicing of Snapshot Camera Images Using Deep Learning

Eric L. Wisotzky, Charul Daudkhane, Anna Hilsmann +1

Spectral imaging technologies have rapidly evolved during the past decades. The recent development of single-camera-one-shot techniques for hyperspectral imaging allows multiple sp…

cs.CV2022★ 26 cited

Perfusion assessment via local remote photoplethysmography (rPPG)

Benjamin Kossack, Eric Wisotzky, Peter Eisert +3

This paper presents an approach to assess the perfusion of visible human tissue from RGB video files. We propose metrics derived from remote photoplethysmography (rPPG) signals to…

cs.CV2022★ 5 cited

Accurate Human Body Reconstruction for Volumetric Video

Decai Chen, Markus Worchel, Ingo Feldmann +2

In this work, we enhance a professional end-to-end volumetric video production pipeline to achieve high-fidelity human body reconstruction using only passive cameras. While current…

cs.CV2022★ 10 cited

From Explanations to Segmentation: Using Explainable AI for Image Segmentation

Clemens Seibold, Johannes Künzel, Anna Hilsmann +1

The new era of image segmentation leveraging the power of Deep Neural Nets (DNNs) comes with a price tag: to train a neural network for pixel-wise segmentation, a large amount of t…

cs.CV2022★ 10 cited

Combining Local and Global Pose Estimation for Precise Tracking of Similar Objects

Niklas Gard, Anna Hilsmann, Peter Eisert

In this paper, we present a multi-object 6D detection and tracking pipeline for potentially similar and non-textured objects. The combination of a convolutional neural network for…

cs.CV2021★ 4 cited

Automated Damage Inspection of Power Transmission Towers from UAV Images

Aleixo Cambeiro Barreiro, Clemens Seibold, Anna Hilsmann +1

Infrastructure inspection is a very costly task, requiring technicians to access remote or hard-to-reach places. This is the case for power transmission towers, which are sparsely…

cs.CV2021★ 5 cited

Zero in on Shape: A Generic 2D-3D Instance Similarity Metric learned from Synthetic Data

Maciej Janik, Niklas Gard, Anna Hilsmann +1

We present a network architecture which compares RGB images and untextured 3D models by the similarity of the represented shape. Our system is optimised for zero-shot retrieval, me…