204 citations · 281 across the 24 of their papers we have counts for
28 papers
S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentation
Leon Sick, Lukas Hoyer, Dominik Engel +2
In recent years, the state-of-the-art in unsupervised video instance segmentation has heavily relied on synthetic video data, generated from object-centric image datasets such as I…
Unified Semantic Transformer for 3D Scene Understanding
Sebastian Koch, Johanna Wald, Hidenobu Matsuki +3
Holistic 3D scene understanding involves capturing and parsing unstructured 3D environments. Due to the inherent complexity of the real world, existing models have predominantly be…
Action-guided generation of 3D functionality segmentation data
Jaime Corsetti, Francesco Giuliari, Davide Boscaini +6
3D functionality segmentation aims to identify the interactive element in a 3D scene required to perform an action described in free-form language (e.g., the handle to ``Open the s…
OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields
Lisa Weijler, Sebastian Koch, Fabio Poiesi +2
Modeling the inherent hierarchical structure of 3D objects and 3D scenes is highly desirable, as it enables a more holistic understanding of environments for autonomous agents. Acc…
Marching Neurons: Accurate Surface Extraction for Neural Implicit Shapes
Christian Stippel, Felix Mujkanovic, Thomas Leimkühler +1
Accurate surface geometry representation is crucial in 3D visual computing. Explicit representations, such as polygonal meshes, and implicit representations, like signed distance f…
Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images
Hannah Kniesel, Leon Sick, Tristan Payer +5
Current state-of-the-art methods for object detection rely on annotated bounding boxes of large data sets for training. However, obtaining such annotations is expensive and can req…
Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation Datasets
Hannah Kniesel, Pedro Hermosilla, Timo Ropinski
Recent advances in conditional image generation from diffusion models have shown great potential in achieving impressive image quality while preserving the constraints introduced b…
RelationField: Relate Anything in Radiance Fields
Sebastian Koch, Johanna Wald, Mirco Colosi +4
Neural radiance fields are an emerging 3D scene representation and recently even been extended to learn features for scene understanding by distilling open-vocabulary features from…
CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation
Leon Sick, Dominik Engel, Sebastian Hartwig +2
Traditionally, algorithms that learn to segment object instances in 2D images have heavily relied on large amounts of human-annotated data. Only recently, novel approaches have eme…
Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships
Sebastian Koch, Narunas Vaskevicius, Mirco Colosi +2
Current approaches for 3D scene graph prediction rely on labeled datasets to train models for a fixed set of known object classes and relationship categories. We present Open3DSG,…
Attention-Guided Masked Autoencoders For Learning Image Representations
Leon Sick, Dominik Engel, Pedro Hermosilla +1
Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks. While vanilla MAEs put equal emphasis on recons…
Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph prediction
Sebastian Koch, Pedro Hermosilla, Narunas Vaskevicius +2
D scene graphs are an emerging 3D scene representation, that models both the objects present in the scene as well as their relationships. However, learning 3D scene graphs is a cha…
SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction
Sebastian Koch, Pedro Hermosilla, Narunas Vaskevicius +2
In the field of 3D scene understanding, 3D scene graphs have emerged as a new scene representation that combines geometric and semantic information about objects and their relation…
Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling
Leon Sick, Dominik Engel, Pedro Hermosilla +1
Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learnin…
HPSCAN: Human Perception-Based Scattered Data Clustering
Sebastian Hartwig, Christian van Onzenoodt, Dominik Engel +2
Cluster separation is a task typically tackled by widely used clustering techniques, such as k-means or DBSCAN. However, these algorithms are based on non-perceptual metrics, and o…
Weakly-Supervised Optical Flow Estimation for Time-of-Flight
Michael Schelling, Pedro Hermosilla, Timo Ropinski
Indirect Time-of-Flight (iToF) cameras are a widespread type of 3D sensor, which perform multiple captures to obtain depth values of the captured scene. While recent approaches to…
Contrastive Representation Learning for 3D Protein Structures
Pedro Hermosilla, Timo Ropinski
Learning from 3D protein structures has gained wide interest in protein modeling and structural bioinformatics. Unfortunately, the number of available structures is orders of magni…
Clean Implicit 3D Structure from Noisy 2D STEM Images
Hannah Kniesel, Timo Ropinski, Tim Bergner +5
Scanning Transmission Electron Microscopes (STEMs) acquire 2D images of a 3D sample on the scale of individual cell components. Unfortunately, these 2D images can be too noisy to b…
Gaussian Mixture Convolution Networks
Adam Celarek, Pedro Hermosilla, Bernhard Kerbl +2
This paper proposes a novel method for deep learning based on the analytical convolution of multidimensional Gaussian mixtures. In contrast to tensors, these do not suffer from the…
Variance-Aware Weight Initialization for Point Convolutional Neural Networks
Pedro Hermosilla, Michael Schelling, Tobias Ritschel +1
Appropriate weight initialization has been of key importance to successfully train neural networks. Recently, batch normalization has diminished the role of weight initialization b…
RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoising
Michael Schelling, Pedro Hermosilla, Timo Ropinski
Time-of-Flight (ToF) cameras are subject to high levels of noise and distortions due to Multi-Path-Interference (MPI). While recent research showed that 2D neural networks are able…
Data-driven deep density estimation
Patrik Puchert, Pedro Hermosilla, Tobias Ritschel +1
Density estimation plays a crucial role in many data analysis tasks, as it infers a continuous probability density function (PDF) from discrete samples. Thus, it is used in tasks a…
Intrinsic-Extrinsic Convolution and Pooling for Learning on 3D Protein Structures
Pedro Hermosilla, Marco Schäfer, Matěj Lang +6
Proteins perform a large variety of functions in living organisms, thus playing a key role in biology. As of now, available learning algorithms to process protein data do not consi…
Enabling Viewpoint Learning through Dynamic Label Generation
Michael Schelling, Pedro Hermosilla, Pere-Pau Vazquez +1
Optimal viewpoint prediction is an essential task in many computer graphics applications. Unfortunately, common viewpoint qualities suffer from two major drawbacks: dependency on c…