no code implementations • 8 Nov 2023 • Robert Johanson, Christian Wilms, Ole Johannsen, Simone Frintrop
However, crop detection, e. g., apple detection in orchard environments remains challenging due to a lack of large-scale datasets and the small relative size of the crops in the image.
no code implementations • 9 Aug 2023 • André Peter Kelm, Niels Hannemann, Bruno Heberle, Lucas Schmidt, Tim Rolff, Christian Wilms, Ehsan Yaghoubi, Simone Frintrop
Our proposed topology also comes with a built-in top-down attention mechanism, which allows processing to be directly influenced by either enhancing or inhibiting category-specific high-level features, drawing parallels to the selective attention mechanism observed in human cognition.
no code implementations • 27 Jul 2023 • Tom Sanitz, Christian Wilms, Simone Frintrop
Traffic light detection is a challenging problem in the context of self-driving cars and driver assistance systems.
no code implementations • 2 Jun 2023 • Julius Richter, Simone Frintrop, Timo Gerkmann
This paper introduces an audio-visual speech enhancement system that leverages score-based generative models, also known as diffusion models, conditioned on visual information.
1 code implementation • 15 Apr 2023 • Pia Čuk, Robin Senge, Mikko Lauri, Simone Frintrop
We investigate cross-quality knowledge distillation (CQKD), a knowledge distillation method where knowledge from a teacher network trained with full-resolution images is transferred to a student network that takes as input low-resolution images.
1 code implementation • 24 Nov 2022 • Ke Li, Tim Rolff, Susanne Schmidt, Reinhard Bacher, Simone Frintrop, Wim Leemans, Frank Steinicke
In this paper, we present and evaluate a NeRF-based framework that is capable of rendering scenes in immersive VR allowing users to freely move their heads to explore complex real-world scenes.
no code implementations • 21 Mar 2022 • Christian Wilms, Alexander Michael Gerlach, Rüdiger Schmitz, Simone Frintrop
Our evaluation in an object proposal generation framework shows that our adapted AttentionMask system is robust to image degradations, generalizes well to unseen types of surgeries, and copes well with small instruments.
no code implementations • 23 Feb 2022 • Christian Wilms, Robert Johanson, Simone Frintrop
Since the apples are very small objects in such scenarios, we tackle this problem by adapting the object proposal generation system AttentionMask that focuses on small objects.
no code implementations • 7 Aug 2021 • Christian Wilms, Simone Frintrop
Class-agnostic object proposal generation is an important first step in many object detection pipelines.
1 code implementation • 2 Mar 2021 • Ge Gao, Mikko Lauri, Xiaolin Hu, Jianwei Zhang, Simone Frintrop
In contrast, this domain gap is considerably smaller and easier to fill for depth information.
1 code implementation • 12 Feb 2021 • Haoran Chen, Jianmin Li, Simone Frintrop, Xiaolin Hu
We cleaned the MSR-VTT annotations by removing these problems, then tested several typical video captioning models on the cleaned dataset.
1 code implementation • 12 Jan 2021 • Christian Wilms, Simone Frintrop
Precise segmentation of objects is an important problem in tasks like class-agnostic object proposal generation or instance segmentation.
no code implementations • 4 Jul 2020 • Mikko Lauri, Joni Pajarinen, Jan Peters, Simone Frintrop
We consider the problem of creating a 3D model using depth images captured by a team of multiple robots.
1 code implementation • 24 Jan 2020 • Ge Gao, Mikko Lauri, Yulong Wang, Xiaolin Hu, Jianwei Zhang, Simone Frintrop
We use depth information represented by point clouds as the input to both deep networks and geometry-based pose refinement and use separate networks for rotation and translation regression.
1 code implementation • 21 Nov 2018 • Christian Wilms, Simone Frintrop
We propose a novel approach for class-agnostic object proposal generation, which is efficient and especially well-suited to detect small objects.
no code implementations • 10 Nov 2018 • Soubarna Banik, Mikko Lauri, Simone Frintrop
With this inspiration, a deep convolutional neural network for low-level object attribute classification, called the Deep Attribute Network (DAN), is proposed.
no code implementations • 16 Aug 2018 • Ge Gao, Mikko Lauri, Jianwei Zhang, Simone Frintrop
Rotation estimation of known rigid objects is important for robotic applications such as dexterous manipulation.
no code implementations • 13 Apr 2017 • Ge Gao, Mikko Lauri, Jianwei Zhang, Simone Frintrop
We propose a new saliency-guided method for generating supervoxels in 3D space.
1 code implementation • 12 Apr 2017 • Mikko Lauri, Simone Frintrop
In application domains such as robotics, it is useful to represent the uncertainty related to the robot's belief about the state of its environment.
no code implementations • 7 Mar 2017 • Mikko Lauri, Eero Heinänen, Simone Frintrop
We address the problem of coordinating the actions of a team of robots with periodic communication capability executing an information gathering task.
no code implementations • CVPR 2015 • Simone Frintrop, Thomas Werner, German Martin Garcia
In this paper, we show that the seminal, biologically-inspired saliency model by Itti et al. is still competitive with current state-of-the-art methods for salient object segmentation if some important adaptions are made.