Accurately and reliably positioning pedestrians in satellite-denied conditions remains a significant challenge. Pedestrian dead reckoning (PDR) is commonly employed to estimate pedestrian location using low-cost inertial sensor. However, PDR is susceptible to drift due to sensor noise, incorrect step detection, and inaccurate stride length estimation. This work proposes ReLoc-PDR, a fusion framework combining PDR and visual relocalization using graph optimization. ReLoc-PDR leverages time-correlated visual observations and learned descriptors to achieve robust positioning in visually-degraded environments. A graph optimization-based fusion mechanism with the Tukey kernel effectively corrects cumulative errors and mitigates the impact of abnormal visual observations. Real-world experiments demonstrate that our ReLoc-PDR surpasses representative methods in accuracy and robustness, achieving accurte and robust pedestrian positioning results using only a smartphone in challenging environments such as less-textured corridors and dark nighttime scenarios.
相關內容
Conditional 3D generation is undergoing a significant advancement, enabling the free creation of 3D content from inputs such as text or 2D images. However, previous approaches have suffered from low inference efficiency, limited generation categories, and restricted downstream applications. In this work, we revisit the impact of different 3D representations on generation quality and efficiency. We propose a progressive generation method through Voxel-Point Progressive Representation (VPP). VPP leverages structured voxel representation in the proposed Voxel Semantic Generator and the sparsity of unstructured point representation in the Point Upsampler, enabling efficient generation of multi-category objects. VPP can generate high-quality 8K point clouds within 0.2 seconds. Additionally, the masked generation Transformer allows for various 3D downstream tasks, such as generation, editing, completion, and pre-training. Extensive experiments demonstrate that VPP efficiently generates high-fidelity and diverse 3D shapes across different categories, while also exhibiting excellent representation transfer performance. Codes will be released at \url{//github.com/qizekun/VPP}.
Neural image classifiers are known to undergo severe performance degradation when exposed to inputs that exhibit covariate shifts with respect to the training distribution. A general interventional data augmentation (IDA)mechanism that simulates arbitrary interventions over spurious variables has often been conjectured as a theoretical solution to this problem and approximated to varying degrees of success. In this work, we study how well modern Text-to-Image (T2I) generators and associated image editing techniques can solve the problem of IDA. We experiment across a diverse collection of benchmarks in domain generalization, ablating across key dimensions of T2I generation, including interventional prompts, conditioning mechanisms, and post-hoc filtering, showing that it substantially outperforms previously state-of-the-art image augmentation techniques independently of how each dimension is configured. We discuss the comparative advantages of using T2I for image editing versus synthesis, also finding that a simple retrieval baseline presents a surprisingly effective alternative, which raises interesting questions about how generative models should be evaluated in the context of domain generalization.
Recent advancements in 4D scene reconstruction using neural radiance fields (NeRF) have demonstrated the ability to represent dynamic scenes from multi-view videos. However, they fail to reconstruct the dynamic scenes and struggle to fit even the training views in unsynchronized settings. It happens because they employ a single latent embedding for a frame while the multi-view images at the frame were actually captured at different moments. To address this limitation, we introduce time offsets for individual unsynchronized videos and jointly optimize the offsets with NeRF. By design, our method is applicable for various baselines and improves them with large margins. Furthermore, finding the offsets naturally works as synchronizing the videos without manual effort. Experiments are conducted on the common Plenoptic Video Dataset and a newly built Unsynchronized Dynamic Blender Dataset to verify the performance of our method. Project page: //seoha-kim.github.io/sync-nerf
Facial style transfer has been quite popular among researchers due to the rise of emerging technologies such as eXtended Reality (XR), Metaverse, and Non-Fungible Tokens (NFTs). Furthermore, StyleGAN methods along with transfer-learning strategies have reduced the problem of limited data to some extent. However, most of the StyleGAN methods overfit the styles while adding artifacts to facial images. In this paper, we propose a facial pose awareness and style transfer (Face-PAST) network that preserves facial details and structures while generating high-quality stylized images. Dual StyleGAN inspires our work, but in contrast, our work uses a pre-trained style generation network in an external style pass with a residual modulation block instead of a transform coding block. Furthermore, we use the gated mapping unit and facial structure, identity, and segmentation losses to preserve the facial structure and details. This enables us to train the network with a very limited amount of data while generating high-quality stylized images. Our training process adapts curriculum learning strategy to perform efficient and flexible style mixing in the generative space. We perform extensive experiments to show the superiority of Face-PAST in comparison to existing state-of-the-art methods.
Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emerges as a solution to optimize policies while simultaneously adhering to multiple constraints, thereby addressing the challenge of integrating reinforcement learning in safety-critical scenarios. In this paper, we present an environment suite called Safety-Gymnasium, which encompasses safety-critical tasks in both single and multi-agent scenarios, accepting vector and vision-only input. Additionally, we offer a library of algorithms named Safe Policy Optimization (SafePO), comprising 16 state-of-the-art SafeRL algorithms. This comprehensive library can serve as a validation tool for the research community. By introducing this benchmark, we aim to facilitate the evaluation and comparison of safety performance, thus fostering the development of reinforcement learning for safer, more reliable, and responsible real-world applications. The website of this project can be accessed at //sites.google.com/view/safety-gymnasium.
The generative Artificial Intelligence (AI) tools based on Large Language Models (LLMs) use billions of parameters to extensively analyse large datasets and extract critical private information such as, context, specific details, identifying information etc. This have raised serious threats to user privacy and reluctance to use such tools. This article proposes the conceptual model called PrivChatGPT, a privacy-preserving model for LLMs that consists of two main components i.e., preserving user privacy during the data curation/pre-processing together with preserving private context and the private training process for large-scale data. To demonstrate its applicability, we show how a private mechanism could be integrated into the existing model for training LLMs to protect user privacy; specifically, we employed differential privacy and private training using Reinforcement Learning (RL). We measure the privacy loss and evaluate the measure of uncertainty or randomness once differential privacy is applied. It further recursively evaluates the level of privacy guarantees and the measure of uncertainty of public database and resources, during each update when new information is added for training purposes. To critically evaluate the use of differential privacy for private LLMs, we hypothetically compared other mechanisms e..g, Blockchain, private information retrieval, randomisation, for various performance measures such as the model performance and accuracy, computational complexity, privacy vs. utility etc. We conclude that differential privacy, randomisation, and obfuscation can impact utility and performance of trained models, conversely, the use of ToR, Blockchain, and PIR may introduce additional computational complexity and high training latency. We believe that the proposed model could be used as a benchmark for proposing privacy preserving LLMs for generative AI tools.
We propose VQ-NeRF, a two-branch neural network model that incorporates Vector Quantization (VQ) to decompose and edit reflectance fields in 3D scenes. Conventional neural reflectance fields use only continuous representations to model 3D scenes, despite the fact that objects are typically composed of discrete materials in reality. This lack of discretization can result in noisy material decomposition and complicated material editing. To address these limitations, our model consists of a continuous branch and a discrete branch. The continuous branch follows the conventional pipeline to predict decomposed materials, while the discrete branch uses the VQ mechanism to quantize continuous materials into individual ones. By discretizing the materials, our model can reduce noise in the decomposition process and generate a segmentation map of discrete materials. Specific materials can be easily selected for further editing by clicking on the corresponding area of the segmentation outcomes. Additionally, we propose a dropout-based VQ codeword ranking strategy to predict the number of materials in a scene, which reduces redundancy in the material segmentation process. To improve usability, we also develop an interactive interface to further assist material editing. We evaluate our model on both computer-generated and real-world scenes, demonstrating its superior performance. To the best of our knowledge, our model is the first to enable discrete material editing in 3D scenes.
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 and suppresses unrelated ones, generating 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 //github.com/XueZ-phd/TFDet.git.
We present CoDEx, a set of knowledge graph completion datasets extracted from Wikidata and Wikipedia that improve upon existing knowledge graph completion benchmarks in scope and level of difficulty. In terms of scope, CoDEx comprises three knowledge graphs varying in size and structure, multilingual descriptions of entities and relations, and tens of thousands of hard negative triples that are plausible but verified to be false. To characterize CoDEx, we contribute thorough empirical analyses and benchmarking experiments. First, we analyze each CoDEx dataset in terms of logical relation patterns. Next, we report baseline link prediction and triple classification results on CoDEx for five extensively tuned embedding models. Finally, we differentiate CoDEx from the popular FB15K-237 knowledge graph completion dataset by showing that CoDEx covers more diverse and interpretable content, and is a more difficult link prediction benchmark. Data, code, and pretrained models are available at //bit.ly/2EPbrJs.
We propose a knowledge-enhanced approach, ERNIE-ViL, to learn joint representations of vision and language. ERNIE-ViL tries to construct the detailed semantic connections (objects, attributes of objects and relationships between objects in visual scenes) across vision and language, which are essential to vision-language cross-modal tasks. Incorporating knowledge from scene graphs, ERNIE-ViL constructs Scene Graph Prediction tasks, i.e., Object Prediction, Attribute Prediction and Relationship Prediction in the pre-training phase. More specifically, these prediction tasks are implemented by predicting nodes of different types in the scene graph parsed from the sentence. Thus, ERNIE-ViL can model the joint representation characterizing the alignments of the detailed semantics across vision and language. Pre-trained on two large image-text alignment datasets (Conceptual Captions and SBU), ERNIE-ViL learns better and more robust joint representations. It achieves state-of-the-art performance on 5 vision-language downstream tasks after fine-tuning ERNIE-ViL. Furthermore, it ranked the 1st place on the VCR leader-board with an absolute improvement of 3.7%.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191