Current MRI super-resolution (SR) methods only use existing contrasts acquired from typical clinical sequences as input for the neural network (NN). In turbo spin echo sequences (TSE) the sequence parameters can have a strong influence on the actual resolution of the acquired image and have consequently a considera-ble impact on the performance of the NN. We propose a known-operator learning approach to perform an end-to-end optimization of MR sequence and neural net-work parameters for SR-TSE. This MR-physics-informed training procedure jointly optimizes the radiofrequency pulse train of a proton density- (PD-) and T2-weighted TSE and a subsequently applied convolutional neural network to predict the corresponding PDw and T2w super-resolution TSE images. The found radiofrequency pulse train designs generate an optimal signal for the NN to perform the SR task. Our method generalizes from the simulation-based optimi-zation to in vivo measurements and the acquired physics-informed SR images show higher correlation with a time-consuming segmented high-resolution TSE sequence compared to a pure network training approach.
Reconstructing semantic 3D building models at the level of detail (LoD) 3 is a long-standing challenge. Unlike mesh-based models, they require watertight geometry and object-wise semantics at the fa\c{c}ade level. The principal challenge of such demanding semantic 3D reconstruction is reliable fa\c{c}ade-level semantic segmentation of 3D input data. We present a novel method, called Scan2LoD3, that accurately reconstructs semantic LoD3 building models by improving fa\c{c}ade-level semantic 3D segmentation. To this end, we leverage laser physics and 3D building model priors to probabilistically identify model conflicts. These probabilistic physical conflicts propose locations of model openings: Their final semantics and shapes are inferred in a Bayesian network fusing multimodal probabilistic maps of conflicts, 3D point clouds, and 2D images. To fulfill demanding LoD3 requirements, we use the estimated shapes to cut openings in 3D building priors and fit semantic 3D objects from a library of fa\c{c}ade objects. Extensive experiments on the TUM city campus datasets demonstrate the superior performance of the proposed Scan2LoD3 over the state-of-the-art methods in fa\c{c}ade-level detection, semantic segmentation, and LoD3 building model reconstruction. We believe our method can foster the development of probability-driven semantic 3D reconstruction at LoD3 since not only the high-definition reconstruction but also reconstruction confidence becomes pivotal for various applications such as autonomous driving and urban simulations.
The ability of convolutional neural networks (CNNs) to recognize objects regardless of their position in the image is due to the translation-equivariance of the convolutional operation. Group-equivariant CNNs transfer this equivariance to other transformations of the input. Dealing appropriately with objects and object parts of different scale is challenging, and scale can vary for multiple reasons such as the underlying object size or the resolution of the imaging modality. In this paper, we propose a scale-equivariant convolutional network layer for three-dimensional data that guarantees scale-equivariance in 3D CNNs. Scale-equivariance lifts the burden of having to learn each possible scale separately, allowing the neural network to focus on higher-level learning goals, which leads to better results and better data-efficiency. We provide an overview of the theoretical foundations and scientific work on scale-equivariant neural networks in the two-dimensional domain. We then transfer the concepts from 2D to the three-dimensional space and create a scale-equivariant convolutional layer for 3D data. Using the proposed scale-equivariant layer, we create a scale-equivariant U-Net for medical image segmentation and compare it with a non-scale-equivariant baseline method. Our experiments demonstrate the effectiveness of the proposed method in achieving scale-equivariance for 3D medical image analysis. We publish our code at https://github.com/wimmerth/scale-equivariant-3d-convnet for further research and application.
Calibrating deep learning models to yield uncertainty-aware predictions is crucial as deep neural networks get increasingly deployed in safety-critical applications. While existing post-hoc calibration methods achieve impressive results on in-domain test datasets, they are limited by their inability to yield reliable uncertainty estimates in domain-shift and out-of-domain (OOD) scenarios. We aim to bridge this gap by proposing DAC, an accuracy-preserving as well as Density-Aware Calibration method based on k-nearest-neighbors (KNN). In contrast to existing post-hoc methods, we utilize hidden layers of classifiers as a source for uncertainty-related information and study their importance. We show that DAC is a generic method that can readily be combined with state-of-the-art post-hoc methods. DAC boosts the robustness of calibration performance in domain-shift and OOD, while maintaining excellent in-domain predictive uncertainty estimates. We demonstrate that DAC leads to consistently better calibration across a large number of model architectures, datasets, and metrics. Additionally, we show that DAC improves calibration substantially on recent large-scale neural networks pre-trained on vast amounts of data.
We propose the first convex relaxation for multiview triangulation that is robust to both noise and outliers. To this end, we extend existing semidefinite relaxation approaches to loss functions that include a truncated least squares cost to account for outliers. We propose two formulations, one based on epipolar constraints and one based on the fractional reprojection equations. The first is lower dimensional and remains tight under moderate noise and outlier levels, while the second is higher dimensional and therefore slower but remains tight even under extreme noise and outlier levels. We demonstrate through extensive experiments that the proposed approach allows us to compute provably optimal reconstructions and that empirically the relaxations remain tight even under significant noise and a large percentage of outliers.
Inferring a meaningful geometric scene representation from a single image is a fundamental problem in computer vision. Approaches based on traditional depth map prediction can only reason about areas that are visible in the image. Currently, neural radiance fields (NeRFs) can capture true 3D including color but are too complex to be generated from a single image. As an alternative, we introduce a neural network that predicts an implicit density field from a single image. It maps every location in the frustum of the image to volumetric density. Our network can be trained through self-supervision from only video data. By not storing color in the implicit volume, but directly sampling color from the available views during training, our scene representation becomes significantly less complex compared to NeRFs, and we can train neural networks to predict it. Thus, we can apply volume rendering to perform both depth prediction and novel view synthesis. In our experiments, we show that our method is able to predict meaningful geometry for regions that are occluded in the input image. Additionally, we demonstrate the potential of our approach on three datasets for depth prediction and novel-view synthesis.
Traditional approaches to prediction of future trajectory of road agents rely on knowing information about their past trajectory. This work rather relies only on having knowledge of the current state and intended direction to make predictions for multiple vehicles at intersections. Furthermore, message passing of this information between the vehicles provides each one of them a more holistic overview of the environment allowing for a more informed prediction. This is done by training a neural network which takes the state and intent of the multiple vehicles to predict their future trajectory. Using the intention as an input allows our approach to be extended to additionally control the multiple vehicles to drive towards desired paths. Experimental results demonstrate the robustness of our approach both in terms of trajectory prediction and vehicle control at intersections. The complete training and evaluation code for this work is available here: \url{https://github.com/Dekai21/Multi_Agent_Intersection}.
In this paper, we present a novel visual SLAM and long-term localization benchmark for autonomous driving in challenging conditions based on the large-scale 4Seasons dataset. The proposed benchmark provides drastic appearance variations caused by seasonal changes and diverse weather and illumination conditions. While significant progress has been made in advancing visual SLAM on small-scale datasets with similar conditions, there is still a lack of unified benchmarks representative of real-world scenarios for autonomous driving. We introduce a new unified benchmark for jointly evaluating visual odometry, global place recognition, and map-based visual localization performance which is crucial to successfully enable autonomous driving in any condition. The data has been collected for more than one year, resulting in more than 300 km of recordings in nine different environments ranging from a multi-level parking garage to urban (including tunnels) to countryside and highway. We provide globally consistent reference poses with up to centimeter-level accuracy obtained from the fusion of direct stereo-inertial odometry with RTK GNSS. We evaluate the performance of several state-of-the-art visual odometry and visual localization baseline approaches on the benchmark and analyze their properties. The experimental results provide new insights into current approaches and show promising potential for future research. Our benchmark and evaluation protocols will be available at https://www.4seasons-dataset.com/.
Event cameras offer the capacity to asynchronously capture brightness changes with low latency, high temporal resolution, and high dynamic range. Deploying deep learning methods for classification or other tasks to these sensors typically requires large labeled datasets. Since the amount of labeled event data is tiny compared to the bulk of labeled RGB imagery, the progress of event-based vision has remained limited. To reduce the dependency on labeled event data, we introduce Masked Event Modeling (MEM), a self-supervised pretraining framework for events. Our method pretrains a neural network on unlabeled events, which can originate from any event camera recording. Subsequently, the pretrained model is finetuned on a downstream task leading to an overall better performance while requiring fewer labels. Our method outperforms the state-of-the-art on N-ImageNet, N-Cars, and N-Caltech101, increasing the object classification accuracy on N-ImageNet by 7.96%. We demonstrate that Masked Event Modeling is superior to RGB-based pretraining on a real world dataset.
We propose an end-to-end inverse rendering pipeline called SupeRVol that allows us to recover 3D shape and material parameters from a set of color images in a super-resolution manner. To this end, we represent both the bidirectional reflectance distribution function (BRDF) and the signed distance function (SDF) by multi-layer perceptrons. In order to obtain both the surface shape and its reflectance properties, we revert to a differentiable volume renderer with a physically based illumination model that allows us to decouple reflectance and lighting. This physical model takes into account the effect of the camera's point spread function thereby enabling a reconstruction of shape and material in a super-resolution quality. Experimental validation confirms that SupeRVol achieves state of the art performance in terms of inverse rendering quality. It generates reconstructions that are sharper than the individual input images, making this method ideally suited for 3D modeling from low-resolution imagery.