Nowadays, autonomous cars can drive smoothly in ordinary cases, and it is widely recognized that realistic sensor simulation will play a critical role in solving remaining corner cases by simulating them. To this end, we propose an autonomous driving simulator based upon neural radiance fields (NeRFs). Compared with existing works, ours has three notable features: (1) Instance-aware. Our simulator models the foreground instances and background environments separately with independent networks so that the static (e.g., size and appearance) and dynamic (e.g., trajectory) properties of instances can be controlled separately. (2) Modular. Our simulator allows flexible switching between different modern NeRF-related backbones, sampling strategies, input modalities, etc. We expect this modular design to boost academic progress and industrial deployment of NeRF-based autonomous driving simulation. (3) Realistic. Our simulator set new state-of-the-art photo-realism results given the best module selection. Our simulator will be open-sourced while most of our counterparts are not. Project page: //open-air-sun.github.io/mars/.
相關內容
Kinship verification is an emerging task in computer vision with multiple potential applications. However, there's no large enough kinship dataset to train a representative and robust model, which is a limitation for achieving better performance. Moreover, face verification is known to exhibit bias, which has not been dealt with by previous kinship verification works and sometimes even results in serious issues. So we first combine existing kinship datasets and label each identity with the correct race in order to take race information into consideration and provide a larger and complete dataset, called KinRace dataset. Secondly, we propose a multi-task learning model structure with attention module to enhance accuracy, which surpasses state-of-the-art performance. Lastly, our fairness-aware contrastive loss function with adversarial learning greatly mitigates racial bias. We introduce a debias term into traditional contrastive loss and implement gradient reverse in race classification task, which is an innovative idea to mix two fairness methods to alleviate bias. Exhaustive experimental evaluation demonstrates the effectiveness and superior performance of the proposed KFC in both standard deviation and accuracy at the same time.
World models, especially in autonomous driving, are trending and drawing extensive attention due to their capacity for comprehending driving environments. The established world model holds immense potential for the generation of high-quality driving videos, and driving policies for safe maneuvering. However, a critical limitation in relevant research lies in its predominant focus on gaming environments or simulated settings, thereby lacking the representation of real-world driving scenarios. Therefore, we introduce DriveDreamer, a pioneering world model entirely derived from real-world driving scenarios. Regarding that modeling the world in intricate driving scenes entails an overwhelming search space, we propose harnessing the powerful diffusion model to construct a comprehensive representation of the complex environment. Furthermore, we introduce a two-stage training pipeline. In the initial phase, DriveDreamer acquires a deep understanding of structured traffic constraints, while the subsequent stage equips it with the ability to anticipate future states. The proposed DriveDreamer is the first world model established from real-world driving scenarios. We instantiate DriveDreamer on the challenging nuScenes benchmark, and extensive experiments verify that DriveDreamer empowers precise, controllable video generation that faithfully captures the structural constraints of real-world traffic scenarios. Additionally, DriveDreamer enables the generation of realistic and reasonable driving policies, opening avenues for interaction and practical applications.
Data-driven approaches hold promise for audio captioning. However, the development of audio captioning methods can be biased due to the limited availability and quality of text-audio data. This paper proposes a SynthAC framework, which leverages recent advances in audio generative models and commonly available text corpus to create synthetic text-audio pairs, thereby enhancing text-audio representation. Specifically, the text-to-audio generation model, i.e., AudioLDM, is used to generate synthetic audio signals with captions from an image captioning dataset. Our SynthAC expands the availability of well-annotated captions from the text-vision domain to audio captioning, thus enhancing text-audio representation by learning relations within synthetic text-audio pairs. Experiments demonstrate that our SynthAC framework can benefit audio captioning models by incorporating well-annotated text corpus from the text-vision domain, offering a promising solution to the challenge caused by data scarcity. Furthermore, SynthAC can be easily adapted to various state-of-the-art methods, leading to substantial performance improvements.
Pedestrian detection plays a critical role in computer vision as it contributes to ensuring traffic safety. Existing methods that rely solely on RGB images suffer from performance degradation under low-light conditions due to the lack of useful information. To address this issue, recent multispectral detection approaches have combined thermal images to provide complementary information and have obtained enhanced performances. Nevertheless, few approaches focus on the negative effects of false positives caused by noisy fused feature maps. Different from them, we comprehensively analyze the impacts of false positives on the detection performance and find that enhancing feature contrast can significantly reduce these false positives. In this paper, we propose a novel target-aware fusion strategy for multispectral pedestrian detection, named TFDet. Our fusion strategy highlights the pedestrian-related features while suppressing unrelated ones, resulting in more discriminative fused features. TFDet achieves state-of-the-art performance on both KAIST and LLVIP benchmarks, with an efficiency comparable to the previous state-of-the-art counterpart. Importantly, TFDet performs remarkably well even under low-light conditions, which is a significant advancement for ensuring road safety. The code will be made publicly available at \url{//github.com/XueZ-phd/TFDet.git}.
Directed fuzzing is a dynamic testing technique that focuses exploration on specific, pre targeted program locations. Like other types of fuzzers, directed fuzzers are most effective when maximizing testing speed and precision. To this end, recent directed fuzzers have begun leveraging path pruning: preventing the wasteful testing of program paths deemed irrelevant to reaching a desired target location. Yet, despite code pruning's substantial speedup, current approaches are imprecise failing to capture indirect control flow requiring additional dynamic analyses that diminish directed fuzzers' speeds. Thus, without code pruning that is both fast and precise, directed fuzzers' effectiveness will continue to remain limited. This paper aims to tackle the challenge of upholding both speed and precision in pruning-based directed fuzzing. We show that existing pruning approaches fail to recover common case indirect control flow; and identify opportunities to enhance them with lightweight heuristics namely, function signature matching enabling them to maximize precision without the burden of dynamic analysis. We implement our enhanced pruning as a prototype, TOPr (Target Oriented Pruning), and evaluate it against the leading pruning based and pruning agnostic directed fuzzers SieveFuzz and AFLGo. We show that TOPr's enhanced pruning outperforms these fuzzers in (1) speed (achieving 222% and 73% higher test case throughput, respectively); (2) reachability (achieving 149% and 9% more target relevant coverage, respectively); and (3) bug discovery time (triggering bugs faster 85% and 8%, respectively). Furthermore, TOPr's balance of speed and precision enables it to find 24 new bugs in 5 open source applications, with 18 confirmed by developers, 12 bugs labelled as "Priority - 1. High", and 12 bugs fixed, underscoring the effectiveness of our framework.
Trajectory generation and trajectory prediction are two critical tasks for autonomous vehicles, which generate various trajectories during development and predict the trajectories of surrounding vehicles during operation, respectively. However, despite significant advances in improving their performance, it remains a challenging problem to ensure that the generated/predicted trajectories are realistic, explainable, and physically feasible. Existing model-based methods provide explainable results, but are constrained by predefined model structures, limiting their capabilities to address complex scenarios. Conversely, existing deep learning-based methods have shown great promise in learning various traffic scenarios and improving overall performance, but they often act as opaque black boxes and lack explainability. In this work, we integrate kinematic knowledge with neural stochastic differential equations (SDE) and develop a variational autoencoder based on a novel latent kinematics-aware SDE (LK-SDE) to generate vehicle motions. Our approach combines the advantages of both model-based and deep learning-based techniques. Experimental results demonstrate that our method significantly outperforms baseline approaches in producing realistic, physically-feasible, and precisely-controllable vehicle trajectories, benefiting both generation and prediction tasks.
A problem that plagues robotic grasping is the misalignment of the object and gripper due to difficulties in precise localization, actuation, etc. Under-actuated robotic hands with compliant mechanisms are used to adapt and compensate for these inaccuracies. However, these mechanisms come at the cost of controllability and coordination. For instance, adaptive functions that let the fingers of a two-fingered gripper adapt independently may affect the coordination necessary for grasping small objects. In this work, we develop a two-fingered robotic hand capable of grasping objects that are offset from the gripper's center, while still having the requisite coordination for grasping small objects via a novel gear-type synchronization mechanism with a magnet. This gear synchronization mechanism allows the adaptive finger's tips to be aligned enabling it to grasp objects as small as toothpicks and washers. The magnetic component allows this coordination to automatically turn off when needed, allowing for the grasping of objects that are offset/misaligned from the gripper. This equips the hand with the capability of grasping light, fragile objects (strawberries, creampuffs, etc) to heavy frying pan lids, all while maintaining their position and posture which is vital in numerous applications that require precise positioning or careful manipulation.
Survival analysis is a valuable tool for estimating the time until specific events, such as death or cancer recurrence, based on baseline observations. This is particularly useful in healthcare to prognostically predict clinically important events based on patient data. However, existing approaches often have limitations; some focus only on ranking patients by survivability, neglecting to estimate the actual event time, while others treat the problem as a classification task, ignoring the inherent time-ordered structure of the events. Furthermore, the effective utilization of censored samples - training data points where the exact event time is unknown - is essential for improving the predictive accuracy of the model. In this paper, we introduce CenTime, a novel approach to survival analysis that directly estimates the time to event. Our method features an innovative event-conditional censoring mechanism that performs robustly even when uncensored data is scarce. We demonstrate that our approach forms a consistent estimator for the event model parameters, even in the absence of uncensored data. Furthermore, CenTime is easily integrated with deep learning models with no restrictions on batch size or the number of uncensored samples. We compare our approach with standard survival analysis methods, including the Cox proportional-hazard model and DeepHit. Our results indicate that CenTime offers state-of-the-art performance in predicting time-to-death while maintaining comparable ranking performance. Our implementation is publicly available at //github.com/ahmedhshahin/CenTime.
Accurate analytical and numerical modeling of multiscale systems is a daunting task. The need to properly resolve spatial and temporal scales spanning multiple orders of magnitude pushes the limits of both our theoretical models as well as our computational capabilities. Rigorous upscaling techniques enable efficient computation while bounding/tracking errors and helping to make informed cost-accuracy tradeoffs. The biggest challenges arise when the applicability conditions of upscaled models break down. Here, we present a non-intrusive two-way (iterative bottom-up top-down) coupled hybrid model, applied to thermal runaway in battery packs, that combines fine-scale and upscaled equations in the same numerical simulation to achieve predictive accuracy while limiting computational costs. First, we develop two methods with different orders of accuracy to enforce continuity at the coupling boundary. Then, we derive weak (i.e., variational) formulations of the fine-scale and upscaled governing equations for finite element (FE) discretization and numerical implementation in FEniCS. We demonstrate that hybrid simulations can accurately predict the average temperature fields within error bounds determined a priori by homogenization theory. Finally, we demonstrate the computational efficiency of the hybrid algorithm against fine-scale simulations.
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.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191