Monocular depth estimation is a crucial task to measure distance relative to a camera, which is important for applications, such as robot navigation and self-driving. Traditional frame-based methods suffer from performance drops due to the limited dynamic range and motion blur. Therefore, recent works leverage novel event cameras to complement or guide the frame modality via frame-event feature fusion. However, event streams exhibit spatial sparsity, leaving some areas unperceived, especially in regions with marginal light changes. Therefore, direct fusion methods, e.g., RAMNet, often ignore the contribution of the most confident regions of each modality. This leads to structural ambiguity in the modality fusion process, thus degrading the depth estimation performance. In this paper, we propose a novel Spatial Reliability-oriented Fusion Network (SRFNet), that can estimate depth with fine-grained structure at both daytime and nighttime. Our method consists of two key technical components. Firstly, we propose an attention-based interactive fusion (AIF) module that applies spatial priors of events and frames as the initial masks and learns the consensus regions to guide the inter-modal feature fusion. The fused feature are then fed back to enhance the frame and event feature learning. Meanwhile, it utilizes an output head to generate a fused mask, which is iteratively updated for learning consensual spatial priors. Secondly, we propose the Reliability-oriented Depth Refinement (RDR) module to estimate dense depth with the fine-grained structure based on the fused features and masks. We evaluate the effectiveness of our method on the synthetic and real-world datasets, which shows that, even without pretraining, our method outperforms the prior methods, e.g., RAMNet, especially in night scenes. Our project homepage: //vlislab22.github.io/SRFNet.
相關內容
Self-supervised learning has been actively studied in time series domain recently, especially for masked reconstruction. Most of these methods follow the "Pre-training + Fine-tuning" paradigm in which a new decoder replaces the pre-trained decoder to fit for a specific downstream task, leading to inconsistency of upstream and downstream tasks. In this paper, we first point out that the unification of task objectives and adaptation for task difficulty are critical for bridging the gap between time series masked reconstruction and forecasting. By reserving the pre-trained mask token during fine-tuning stage, the forecasting task can be taken as a special case of masked reconstruction, where the future values are masked and reconstructed based on history values. It guarantees the consistency of task objectives but there is still a gap in task difficulty. Because masked reconstruction can utilize contextual information while forecasting can only use historical information to reconstruct. To further mitigate the existed gap, we propose a simple yet effective prompt token tuning (PT-Tuning) paradigm, in which all pre-trained parameters are frozen and only a few trainable prompt tokens are added to extended mask tokens in element-wise manner. Extensive experiments on real-world datasets demonstrate the superiority of our proposed paradigm with state-of-the-art performance compared to representation learning and end-to-end supervised forecasting methods.
Aerial mapping systems are important for many surveying applications (e.g., industrial inspection or agricultural monitoring). Semi-autonomous mapping with GPS-guided aerial platforms that fly preplanned missions is already widely available but fully autonomous systems can significantly improve efficiency. Autonomously mapping complex 3D structures requires a system that performs online mapping and mission planning. This paper presents Osprey, an autonomous aerial mapping system with state-of-the-art multi-session mapping capabilities. It enables a non-expert operator to specify a bounded target area that the aerial platform can then map autonomously, over multiple flights if necessary. Field experiments with Osprey demonstrate that this system can achieve greater map coverage of large industrial sites than manual surveys with a pilot-flown aerial platform or a terrestrial laser scanner (TLS). Three sites, with a total ground coverage of $7085$ m$^2$ and a maximum height of $27$ m, were mapped in separate missions using $112$ minutes of autonomous flight time. True colour maps were created from images captured by Osprey using pointcloud and NeRF reconstruction methods. These maps provide useful data for structural inspection tasks.
Deploying and testing cellular networks is a complex task due to the multitude of components involved-from the core to the Radio Access Network (RAN) and the User Equipments (UEs) -- all of which require integration and constant monitoring. Interference and the inherent randomness of the wireless channel further complicate the issue, posing additional challenges for repeatable and consistent testing. Consequently, both private and public cellular systems still rely heavily on human intervention for operations such as network reconfiguration, performance monitoring, and conducting end-to-end drive tests. This reliance significantly slows the pace of innovation in cellular systems. To address these challenges, we introduce 5G-CT, an automation framework based on OpenShift and the GitOps workflow, capable of deploying a softwarized end-to-end 5G and O-RAN-compliant system in a matter of seconds. We have deployed 5G-CT to test the integration and performance of popular open-source cellular stacks, including OpenAirInterface (OAI), and have collected months of over-the-air testing results without the need for human intervention. 5G-CT brings cloud-native Continuous Integration (CI) and Continuous Delivery (CD) to the RAN, effectively addressing the complexities associated with managing spectrum, radios, heterogeneous devices, and distributed components. Moreover, it provides much-needed automation and Continuous Testing (CT) for cellular networks.
Thermal spray coating is a critical process in many industries, involving the application of coatings to surfaces to enhance their functionality. This paper proposes a framework for modelling and predicting critical target variables in thermal spray coating processes, based on the application of statistical design of experiments (DoE) and the modelling of the data using generalized linear models (GLMs) and gamma regression. Experimental data obtained from thermal spray coating trials are used to validate the presented approach, demonstrating that it is able to accurately model and predict critical target variables and their intricate relationships. As such, the framework has significant potential for the optimization of thermal spray coating processes, and can contribute to the development of more efficient and effective coating technologies in various industries.
We explore how pre-training a model to infer depth from a single image compares to pre-training the model for a semantic task, e.g. ImageNet classification, for the purpose of downstream transfer to semantic segmentation. The question of whether pre-training on geometric tasks is viable for downstream transfer to semantic tasks is important for two reasons, one practical and the other scientific. In practice, if it were viable, one could reduce pre-training costs and bias due to human annotation at scale. If, however, it were not, then that would affirm human annotation as an inductive vehicle so powerful to justify the annotation effort. Yet the bootstrapping question would still be unanswered: How did the ability to assign labels to semantically coherent regions emerge? If pre-training on a geometric task was sufficient to prime a notion of 'object', leveraging the regularities of the environment (what Gibson called 'detached objects'), that would reduce the gap to semantic inference as a matter of aligning labels, which could be done with few examples. To test these hypotheses, we have designed multiple controlled experiments that require minimal fine-tuning, using common benchmarks such as KITTI, Cityscapes, and NYU-V2: We explore different forms of supervision for depth estimation, training pipelines, and data resolutions for semantic fine-tuning. We find that depth pre-training exceeds performance relative to ImageNet pre-training on average by 5.8% mIoU and 5.2% pixel accuracy. Surprisingly, we find that optical flow estimation, which is a closely related task to depth estimation as it optimizes the same photometric reprojection error, is considerably less effective.
The sequential recommendation system has been widely studied for its promising effectiveness in capturing dynamic preferences buried in users' sequential behaviors. Despite the considerable achievements, existing methods usually focus on intra-sequence modeling while overlooking exploiting global collaborative information by inter-sequence modeling, resulting in inferior recommendation performance. Therefore, previous works attempt to tackle this problem with a global collaborative item graph constructed by pre-defined rules. However, these methods neglect two crucial properties when capturing global collaborative information, i.e., adaptiveness and personalization, yielding sub-optimal user representations. To this end, we propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR), that incorporates adaptive and personalized global collaborative information into sequential recommendation systems. Specifically, we first learn an adaptive global graph among all items and capture global collaborative information with it in a self-supervised fashion, whose computational burden can be further alleviated by the proposed SVD-based accelerator. Furthermore, based on the graph, we propose to extract and utilize personalized item correlations in the form of relative positional encoding, which is a highly compatible manner of personalizing the utilization of global collaborative information. Finally, the entire framework is optimized in a multi-task learning paradigm, thus each part of APGL4SR can be mutually reinforced. As a generic framework, APGL4SR can outperform other baselines with significant margins. The code is available at //github.com/Graph-Team/APGL4SR.
Object rearrangement is a fundamental problem in robotics with various practical applications ranging from managing warehouses to cleaning and organizing home kitchens. While existing research has primarily focused on single-agent solutions, real-world scenarios often require multiple robots to work together on rearrangement tasks. This paper proposes a comprehensive learning-based framework for multi-agent object rearrangement planning, addressing the challenges of task sequencing and path planning in complex environments. The proposed method iteratively selects objects, determines their relocation regions, and pairs them with available robots under kinematic feasibility and task reachability for execution to achieve the target arrangement. Our experiments on a diverse range of simulated and real-world environments demonstrate the effectiveness and robustness of the proposed framework. Furthermore, results indicate improved performance in terms of traversal time and success rate compared to baseline approaches.
Segmentation and tracking of unseen object instances in discrete frames pose a significant challenge in dynamic industrial robotic contexts, such as distribution warehouses. Here, robots must handle object rearrangement, including shifting, removal, and partial occlusion by new items, and track these items after substantial temporal gaps. The task is further complicated when robots encounter objects not learned in their training sets, which requires the ability to segment and track previously unseen items. Considering that continuous observation is often inaccessible in such settings, our task involves working with a discrete set of frames separated by indefinite periods during which substantial changes to the scene may occur. This task also translates to domestic robotic applications, such as rearrangement of objects on a table. To address these demanding challenges, we introduce new synthetic and real-world datasets that replicate these industrial and household scenarios. We also propose a novel paradigm for joint segmentation and tracking in discrete frames along with a transformer module that facilitates efficient inter-frame communication. The experiments we conduct show that our approach significantly outperforms recent methods. For additional results and videos, please visit \href{//sites.google.com/view/stow-corl23}{website}. Code and dataset will be released.
Multi-modal fusion is a fundamental task for the perception of an autonomous driving system, which has recently intrigued many researchers. However, achieving a rather good performance is not an easy task due to the noisy raw data, underutilized information, and the misalignment of multi-modal sensors. In this paper, we provide a literature review of the existing multi-modal-based methods for perception tasks in autonomous driving. Generally, we make a detailed analysis including over 50 papers leveraging perception sensors including LiDAR and camera trying to solve object detection and semantic segmentation tasks. Different from traditional fusion methodology for categorizing fusion models, we propose an innovative way that divides them into two major classes, four minor classes by a more reasonable taxonomy in the view of the fusion stage. Moreover, we dive deep into the current fusion methods, focusing on the remaining problems and open-up discussions on the potential research opportunities. In conclusion, what we expect to do in this paper is to present a new taxonomy of multi-modal fusion methods for the autonomous driving perception tasks and provoke thoughts of the fusion-based techniques in the future.
Most object recognition approaches predominantly focus on learning discriminative visual patterns while overlooking the holistic object structure. Though important, structure modeling usually requires significant manual annotations and therefore is labor-intensive. In this paper, we propose to "look into object" (explicitly yet intrinsically model the object structure) through incorporating self-supervisions into the traditional framework. We show the recognition backbone can be substantially enhanced for more robust representation learning, without any cost of extra annotation and inference speed. Specifically, we first propose an object-extent learning module for localizing the object according to the visual patterns shared among the instances in the same category. We then design a spatial context learning module for modeling the internal structures of the object, through predicting the relative positions within the extent. These two modules can be easily plugged into any backbone networks during training and detached at inference time. Extensive experiments show that our look-into-object approach (LIO) achieves large performance gain on a number of benchmarks, including generic object recognition (ImageNet) and fine-grained object recognition tasks (CUB, Cars, Aircraft). We also show that this learning paradigm is highly generalizable to other tasks such as object detection and segmentation (MS COCO). Project page: //github.com/JDAI-CV/LIO.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191