Virtual Reality (VR) applications constantly strive for more realism, immersion and intuitive user experiences. Traditional VR controllers can hinder full immersion, since they form an additional barrier between the u...
详细信息
Temporal action segmentation in untrimmed videos has gained increased attention recently. However, annotating action classes and frame-wise boundaries is extremely time consuming and cost intensive, especially on larg...
详细信息
The total generalized variation extends the total variation by incorporating higher-order smoothness. Thus, it can also suffer from similar discretization issues related to isotropy. Inspired by the success of novel d...
详细信息
Point cloud registration aligns 3D point clouds using spatial transformations. It is an important task in computervision, with applications in areas such as augmented reality (AR) and medical imaging. This work explo...
详细信息
Stereo estimation has made many advancements in recent years with the introduction of deep-learning. However the traditional supervised approach to deep-learning requires the creation of accurate and plentiful ground-...
详细信息
Many artifacts of our archaeological heritage are preserved only in fragments. The reassembly of these parts to their original form is therefore an essential task for archaeologists. Our project aims at incorporating ...
Rigid registration of point clouds is a fundamental problem in computervision with many applications from 3D scene reconstruction to geometry capture and robotics. If a suitable initial registration is available, con...
Rigid registration of point clouds is a fundamental problem in computervision with many applications from 3D scene reconstruction to geometry capture and robotics. If a suitable initial registration is available, conventional methods like ICP and its many variants can provide adequate solutions. In absence of a suitable initialization and in the presence of a high outlier rate or in the case of small overlap though the task of rigid registration still presents great challenges. The advent of deep learning in computervision has brought new drive to research on this topic, since it provides the possibility to learn expressive feature-representations and provide one-shot estimates instead of depending on time-consuming iterations of conventional robust methods. Yet, the rotation and permutation invariant nature of point clouds poses its own challenges to deep learning, resulting in loss of performance and low generalization capability due to sensitivity to outliers and characteristics of 3D scans not present during network training. In this work, we present a novel fast and light-weight network architecture using the attention mechanism to augment point descriptors at inference time to optimally suit the registration task of the specific point clouds it is presented with. Employing a fully-connected graph both within and between point clouds lets the network reason about the importance and reliability of points for registration, making our approach robust to outliers, low overlap and unseen data. We test the performance of our registration algorithm on different registration and generalization tasks and provide information on runtime and resource consumption. The code and trained weights are available at https://***/mordecaimalignatius/GAFAR/.
Despite that a cross-polarization is a very efficient way to remove undesired reflections and specularities while imaging and digitizing certain type of materials. It does not come, however, with no risk when color fi...
详细信息
A better understanding of interactive pedestrian behavior in critical traffic situations is essential for the development of enhanced pedestrian safety systems. Real-world traffic observations play a decisive role in ...
详细信息
Out-of-distribution (OOD) detection is essential to ensure the reliability and robustness of machine learning models in real-world applications. Post-hoc OOD detection methods have gained significant attention due to ...
Out-of-distribution (OOD) detection is essential to ensure the reliability and robustness of machine learning models in real-world applications. Post-hoc OOD detection methods have gained significant attention due to the fact that they offer the advantage of not requiring additional re-training, which could degrade model performance and increase training time. However, most existing post-hoc methods rely only on the encoder output (features), logits, or the softmax probability, meaning they have no access to information that might be lost in the feature extraction process. In this work, we address this limitation by introducing Adaptive Temperature Scaling (ATS), a novel approach that dynamically calculates a temperature value based on activations of the intermediate layers. Fusing this sample-specific adjustment with class-dependent logits, our ATS captures additional statistical information before they are lost in the feature extraction process, leading to a more robust and powerful OOD detection method. We conduct extensive experiments to demonstrate the efficacy of our approach. Notably, our method can be seamlessly combined with SOTA post-hoc OOD detection methods that rely on the logits, thereby enhancing their performance and improving their robustness.
暂无评论