Search

Directly generating scenes from satellite imagery offers exciting possibilities for integration into applications like games and map services. However, challenges arise from significant view changes and scene scale. Previous efforts mainly focused on image or video generation, lacking exploration into the adaptability of scene generation for arbitrary views. Existing 3D generation works either operate at the object level or are difficult to utilize the geometry obtained from satellite imagery. To overcome these limitations, we propose a novel architecture for direct 3D scene generation by introducing diffusion models into 3D sparse representations and combining them with neural rendering techniques. Specifically, our approach generates texture colors at the point level for a given geometry using a 3D diffusion model first, which is then transformed into a scene representation in a feed-forward manner. The representation can be utilized to render arbitrary views which would excel in both single-frame quality and inter-frame consistency. Experiments in two city-scale datasets show that our model demonstrates proficiency in generating photo-realistic street-view image sequences and cross-view urban scenes from satellite imagery.

The capabilities of monocular depth estimation (MDE) models are limited by the availability of sufficient and diverse datasets. In the case of MDE models for autonomous driving, this issue is exacerbated by the linearity of the captured data trajectories. We propose a NeRF-based data augmentation pipeline to introduce synthetic data with more diverse viewing directions into training datasets and demonstrate the benefits of our approach to model performance and robustness. Our data augmentation pipeline, which we call \textit{NeRFmentation}, trains NeRFs on each scene in a dataset, filters out subpar NeRFs based on relevant metrics, and uses them to generate synthetic RGB-D images captured from new viewing directions. In this work, we apply our technique in conjunction with three state-of-the-art MDE architectures on the popular autonomous driving dataset, KITTI, augmenting its training set of the Eigen split. We evaluate the resulting performance gain on the original test set, a separate popular driving dataset, and our own synthetic test set.

Many complex tasks can be decomposed into simpler, independent parts. Discovering such underlying compositional structure has the potential to enable compositional generalization. Despite progress, our most powerful systems struggle to compose flexibly. It therefore seems natural to make models more modular to help capture the compositional nature of many tasks. However, it is unclear under which circumstances modular systems can discover hidden compositional structure. To shed light on this question, we study a teacher-student setting with a modular teacher where we have full control over the composition of ground truth modules. This allows us to relate the problem of compositional generalization to that of identification of the underlying modules. In particular we study modularity in hypernetworks representing a general class of multiplicative interactions. We show theoretically that identification up to linear transformation purely from demonstrations is possible without having to learn an exponential number of module combinations. We further demonstrate empirically that under the theoretically identified conditions, meta-learning from finite data can discover modular policies that generalize compositionally in a number of complex environments., Comment: Published as a conference paper at ICLR 2024; Code available at https://github.com/smonsays/modular-hyperteacher

We give an explicit description of a diagonal map on the Bardzell resolution for any monomial algebra, and we use this diagonal map to describe the cup product on Hochschild cohomology. Then, we prove that the cup product is zero in positive degrees for triangular monomial algebras. Our proof uses the graded-commutativity of the cup product on Hochschild cohomology and does not rely on explicit computation of the Hochschild cohomology modules., Comment: 20 pages; minor edits for v2; to appear in Journal of Algebra

In automotive applications, frequency modulated continuous wave (FMCW) radar is an established technology to determine the distance, velocity and angle of objects in the vicinity of the vehicle. The quality of predictions might be seriously impaired if mutual interference between radar sensors occurs. Previous work processes data from the entire receiver array in parallel to increase interference mitigation quality using neural networks (NNs). However, these architectures do not generalize well across different angles of arrival (AoAs) of interferences and objects. In this paper we introduce fully convolutional neural network (CNN) with rank-three convolutions which is able to transfer learned patterns between different AoAs. Our proposed architecture outperforms previous work while having higher robustness and a lower number of trainable parameters. We evaluate our network on a diverse data set and demonstrate its angle equivariance., Comment: 4 pages, 3 figures

The scarcity of annotated data in LiDAR point cloud understanding hinders effective representation learning. Consequently, scholars have been actively investigating efficacious self-supervised pre-training paradigms. Nevertheless, temporal information, which is inherent in the LiDAR point cloud sequence, is consistently disregarded. To better utilize this property, we propose an effective pre-training strategy, namely Temporal Masked Auto-Encoders (T-MAE), which takes as input temporally adjacent frames and learns temporal dependency. A SiamWCA backbone, containing a Siamese encoder and a windowed cross-attention (WCA) module, is established for the two-frame input. Considering that the movement of an ego-vehicle alters the view of the same instance, temporal modeling also serves as a robust and natural data augmentation, enhancing the comprehension of target objects. SiamWCA is a powerful architecture but heavily relies on annotated data. Our T-MAE pre-training strategy alleviates its demand for annotated data. Comprehensive experiments demonstrate that T-MAE achieves the best performance on both Waymo and ONCE datasets among competitive self-supervised approaches. Codes will be released at https://github.com/codename1995/T-MAE, Comment: Accepted to ECCV 2024

In this paper we propose a new method for training neural networks (NNs) for frequency modulated continuous wave (FMCW) radar mutual interference mitigation. Instead of training NNs to regress from interfered to clean radar signals as in previous work, we train NNs directly on object detection maps. We do so by performing a continuous relaxation of the cell-averaging constant false alarm rate (CA-CFAR) peak detector, which is a well-established algorithm for object detection using radar. With this new training objective we are able to increase object detection performance by a large margin. Furthermore, we introduce separable convolution kernels to strongly reduce the number of parameters and computational complexity of convolutional NN architectures for radar applications. We validate our contributions with experiments on real-world measurement data and compare them against signal processing interference mitigation methods., Comment: 2023 IEEE International Radar Conference (RADAR), 6 pages, 4 figures

Open-ended image understanding tasks gained significant attention from the research community, particularly with the emergence of Vision-Language Models. Open-Vocabulary Segmentation (OVS) methods are capable of performing semantic segmentation without relying on a fixed vocabulary, and in some cases, they operate without the need for training or fine-tuning. However, OVS methods typically require users to specify the vocabulary based on the task or dataset at hand. In this paper, we introduce \textit{Auto-Vocabulary Semantic Segmentation (AVS)}, advancing open-ended image understanding by eliminating the necessity to predefine object categories for segmentation. Our approach, \ours, presents a framework that autonomously identifies relevant class names using enhanced BLIP embeddings, which are utilized for segmentation afterwards. Given that open-ended object category predictions cannot be directly compared with a fixed ground truth, we develop a Large Language Model-based Auto-Vocabulary Evaluator (LAVE) to efficiently evaluate the automatically generated class names and their corresponding segments. Our method sets new benchmarks on datasets such as PASCAL VOC and Context, ADE20K, and Cityscapes for AVS and showcases competitive performance to OVS methods that require specified class names.

We present a dense simultaneous localization and mapping (SLAM) method that uses 3D Gaussians as a scene representation. Our approach enables interactive-time reconstruction and photo-realistic rendering from real-world single-camera RGBD videos. To this end, we propose a novel effective strategy for seeding new Gaussians for newly explored areas and their effective online optimization that is independent of the scene size and thus scalable to larger scenes. This is achieved by organizing the scene into sub-maps which are independently optimized and do not need to be kept in memory. We further accomplish frame-to-model camera tracking by minimizing photometric and geometric losses between the input and rendered frames. The Gaussian representation allows for high-quality photo-realistic real-time rendering of real-world scenes. Evaluation on synthetic and real-world datasets demonstrates competitive or superior performance in mapping, tracking, and rendering compared to existing neural dense SLAM methods.

We propose an online 3D semantic segmentation method that incrementally reconstructs a 3D semantic map from a stream of RGB-D frames. Unlike offline methods, ours is directly applicable to scenarios with real-time constraints, such as robotics or mixed reality. To overcome the inherent challenges of online methods, we make two main contributions. First, to effectively extract information from the input RGB-D video stream, we jointly estimate geometry and semantic labels per frame in 3D. A key focus of our approach is to reason about semantic entities both in the 2D input and the local 3D domain to leverage differences in spatial context and network architectures. Our method predicts 2D features using an off-the-shelf segmentation network. The extracted 2D features are refined by a lightweight 3D network to enable reasoning about the local 3D structure. Second, to efficiently deal with an infinite stream of input RGB-D frames, a subsequent network serves as a temporal expert predicting the incremental scene updates by leveraging 2D, 3D, and past information in a learned manner. These updates are then integrated into a global scene representation. Using these main contributions, our method can enable scenarios with real-time constraints and can scale to arbitrary scene sizes by processing and updating the scene only in a local region defined by the new measurement. Our experiments demonstrate improved results compared to existing online methods that purely operate in local regions and show that complementary sources of information can boost the performance. We provide a thorough ablation study on the benefits of different architectural as well as algorithmic design decisions. Our method yields competitive results on the popular ScanNet benchmark and SceneNN dataset.

Graph-based interactive theorem provers offer a visual representation of proofs, explicitly representing the dependencies and inferences between each of the proof steps in a graph or hypergraph format. The number and complexity of these dependency links can determine how long it takes to verify the validity of the entire proof. Towards this end, we present a set of parallel algorithms for the formal verification of graph-based natural-deduction (ND) style proofs. We introduce a definition of layering that captures dependencies between the proof steps (nodes). Nodes in each layer can then be verified in parallel as long as prior layers have been verified. To evaluate the performance of our algorithms on proof graphs, we propose a framework for finding the performance bounds and patterns using directed acyclic network topologies (DANTs). This framework allows us to create concrete instances of DANTs for empirical evaluation of our algorithms. With this, we compare our set of parallel algorithms against a serial implementation with two experiments: one scaling both the problem size and the other scaling the number of threads. Our findings show that parallelization results in improved verification performance for certain DANT instances. We also show that our algorithms scale for certain DANT instances with respect to the number of threads., Comment: In Proceedings LFMTP 2023, arXiv:2311.09918

Humans have a remarkable ability to perceive and reason about the world around them by understanding the relationships between objects. In this paper, we investigate the effectiveness of using such relationships for object detection and instance segmentation. To this end, we propose a Relational Prior-based Feature Enhancement Model (RP-FEM), a graph transformer that enhances object proposal features using relational priors. The proposed architecture operates on top of scene graphs obtained from initial proposals and aims to concurrently learn relational context modeling for object detection and instance segmentation. Experimental evaluations on COCO show that the utilization of scene graphs, augmented with relational priors, offer benefits for object detection and instance segmentation. RP-FEM demonstrates its capacity to suppress improbable class predictions within the image while also preventing the model from generating duplicate predictions, leading to improvements over the baseline model on which it is built., Comment: Published in ICCV2023 SG2RL Workshop

The ability to detect objects in images at varying scales has played a pivotal role in the design of modern object detectors. Despite considerable progress in removing hand-crafted components and simplifying the architecture with transformers, multi-scale feature maps and/or pyramid design remain a key factor for their empirical success. In this paper, we show that this reliance on either feature pyramids or an hierarchical backbone is unnecessary and a transformer-based detector with scale-aware attention enables the plain detector `SimPLR' whose backbone and detection head are both non-hierarchical and operate on single-scale features. We find through our experiments that SimPLR with scale-aware attention is plain and simple, yet competitive with multi-scale vision transformer alternatives. Compared to the multi-scale and single-scale state-of-the-art, our model scales much better with bigger capacity (self-supervised) models and more pre-training data, allowing us to report a consistently better accuracy and faster runtime for object detection, instance segmentation as well as panoptic segmentation. Code will be released.

Recent observations are shedding light on the important role that active galactic nuclei (AGN) play in the production of high-energy neutrinos. In this study, we focus on one object, 5BZB J0630-2406, which is among the blazars recently proposed as associated with neutrino emission during the first 7-yr IceCube observations. Modelling the quasi-simultaneous, broad-band spectral energy distribution, we explore various scenarios from purely leptonic to lepto-hadronic models, testing the inclusion of external photon fields. This theoretical study provides a complementary testing ground for the proposed neutrino-blazar association. Despite being historically classified as a BL Lac, our study shows that 5BZB J0630-2406 belongs to the relatively rare sub-class of high-power flat-spectrum radio quasars (FSRQs). Our results indicate that interactions between protons and external radiation fields can produce a neutrino flux that is within the reach of the IceCube detector. Furthermore, the spectral shape of the X-ray emission suggests the imprint of hadronic processes related to very energetic protons., Comment: Accepted for publication. 18 pages, 10 figures

Recent works on SLAM extend their pose graphs with higher-level semantic concepts like Rooms exploiting relationships between them, to provide, not only a richer representation of the situation/environment but also to improve the accuracy of its estimation. Concretely, our previous work, Situational Graphs (S-Graphs+), a pioneer in jointly leveraging semantic relationships in the factor optimization process, relies on semantic entities such as Planes and Rooms, whose relationship is mathematically defined. Nevertheless, there is no unique approach to finding all the hidden patterns in lower-level factor-graphs that correspond to high-level concepts of different natures. It is currently tackled with ad-hoc algorithms, which limits its graph expressiveness. To overcome this limitation, in this work, we propose an algorithm based on Graph Neural Networks for learning high-level semantic-relational concepts that can be inferred from the low-level factor graph. Given a set of mapped Planes our algorithm is capable of inferring Room entities relating to the Planes. Additionally, to demonstrate the versatility of our method, our algorithm can infer an additional semantic-relational concept, i.e. Wall, and its relationship with its Planes. We validate our method in both simulated and real datasets demonstrating improved performance over two baseline approaches. Furthermore, we integrate our method into the S-Graphs+ algorithm providing improved pose and map accuracy compared to the baseline while further enhancing the scene representation.

In this paper, we focus on semantic segmentation method for point clouds of urban scenes. Our fundamental concept revolves around the collaborative utilization of diverse scene representations to benefit from different context information and network architectures. To this end, the proposed network architecture, called APNet, is split into two branches: a point cloud branch and an aerial image branch which input is generated from a point cloud. To leverage the different properties of each branch, we employ a geometry-aware fusion module that is learned to combine the results of each branch. Additional separate losses for each branch avoid that one branch dominates the results, ensure the best performance for each branch individually and explicitly define the input domain of the fusion network assuring it only performs data fusion. Our experiments demonstrate that the fusion output consistently outperforms the individual network branches and that APNet achieves state-of-the-art performance of 65.2 mIoU on the SensatUrban dataset. Upon acceptance, the source code will be made accessible., Comment: Accepted by ICCV Workshop 2023 and selected as an oral

We consider the problem of approximating the regression function from noisy vector-valued data by an online learning algorithm using an appropriate reproducing kernel Hilbert space (RKHS) as prior. In an online algorithm, i.i.d. samples become available one by one by a random process and are successively processed to build approximations to the regression function. We are interested in the asymptotic performance of such online approximation algorithms and show that the expected squared error in the RKHS norm can be bounded by $C^2 (m+1)^{-s/(2+s)}$, where $m$ is the current number of processed data, the parameter $0

The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leaderboards are available on https://www.soccer-net.org. Baselines and development kits can be found on https://github.com/SoccerNet.

Some autoregressive models exhibit in-context learning capabilities: being able to learn as an input sequence is processed, without undergoing any parameter changes, and without being explicitly trained to do so. The origins of this phenomenon are still poorly understood. Here we analyze a series of Transformer models trained to perform synthetic sequence prediction tasks, and discover that standard next-token prediction error minimization gives rise to a subsidiary learning algorithm that adjusts the model as new inputs are revealed. We show that this process corresponds to gradient-based optimization of a principled objective function, which leads to strong generalization performance on unseen sequences. Our findings explain in-context learning as a product of autoregressive loss minimization and inform the design of new optimization-based Transformer layers.

Recognising reinforced concrete defects (RCDs) is a crucial element for determining the structural integrity, traffic safety and durability of bridges. However, most of the existing datasets in the RCD domain are derived from a small number of bridges acquired in specific camera poses, lighting conditions and with fixed hardware. These limitations question the usability of models trained on such open-source data in real-world scenarios. We address this problem by testing such models on our "dacl1k" dataset, a highly diverse RCD dataset for multi-label classification based on building inspections including 1,474 images. Thereby, we trained the models on different combinations of open-source data (meta datasets) which were subsequently evaluated both extrinsically and intrinsically. During extrinsic evaluation, we report metrics on dacl1k and the meta datasets. The performance analysis on dacl1k shows practical usability of the meta data, where the best model shows an Exact Match Ratio of 32%. Additionally, we conduct an intrinsic evaluation by clustering the bottleneck features of the best model derived from the extrinsic evaluation in order to find out, if the model has learned distinguishing datasets or the classes (RCDs) which is the aspired goal. The dacl1k dataset and our trained models will be made publicly available, enabling researchers and practitioners to put their models to the real-world test.

Recent architectural developments have enabled recurrent neural networks (RNNs) to reach and even surpass the performance of Transformers on certain sequence modeling tasks. These modern RNNs feature a prominent design pattern: linear recurrent layers interconnected by feedforward paths with multiplicative gating. Here, we show how RNNs equipped with these two design elements can exactly implement (linear) self-attention, the main building block of Transformers. By reverse-engineering a set of trained RNNs, we find that gradient descent in practice discovers our construction. In particular, we examine RNNs trained to solve simple in-context learning tasks on which Transformers are known to excel and find that gradient descent instills in our RNNs the same attention-based in-context learning algorithm used by Transformers. Our findings highlight the importance of multiplicative interactions in neural networks and suggest that certain RNNs might be unexpectedly implementing attention under the hood.

We have performed a study of several cesium oven designs. A comparison between recirculating (or sticking-wall) or collimating (or reemitting-wall) ovens is made in order to extract the most efficient design in terms of beam brightness. Unfortunately, non-reproducible behaviors have been observed, and the most often observed output flux is similar to the sticking-wall case, which is the lowest theoretical value of the two cases, with a beam brightness close to $10^{18}$ at.sr$^{-1}$.s$^{-1}$.cm$^{-2}$. The reason of this universally observed behavior is unclear despite having tested several materials for the collimating tube. Conclusion on possible improved design based on sticking of cesium on several (un)cleaned surface is given., Comment: This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in Rev Sci Instrum 1 April 2022; 93 (4): 043302 and may be found at https://pubs.aip.org/aip/rsi/article/93/4/043302/2848701