SearcharxivSearch

arXiv subjects

Yaming Wang

Publications and source records attributed to Yaming Wang.

12 recordsLinked to original sources

STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation

The generation of temporally consistent, high-fidelity driving videos over extended horizons presents a fundamental challenge in autonomous driving world modeling. Existing approaches often suffer from error accumulation and feature misalignment due to inadequate decoupling of spatio-temporal dynamics and limited cross-frame feature propagation mechanisms. To address these limitations, we present STAGE (Streaming Temporal Attention Generative Engine), a novel auto-regressive framework that pioneers hierarchical feature coordination and multi-phase optimization for sustainable video synthesis. To achieve high-quality long-horizon driving video generation, we introduce Hierarchical Temporal Feature Transfer (HTFT) and a novel multi-stage training strategy. HTFT enhances temporal consistency between video frames throughout the video generation process by modeling the temporal and denoising process separately and transferring denoising features between frames. The multi-stage training strategy is to divide the training into three stages, through model decoupling and auto-regressive inference process simulation, thereby accelerating model convergence and reducing error accumulation. Experiments on the Nuscenes dataset show that STAGE has significantly surpassed existing methods in the long-horizon driving video generation task. In addition, we also explored STAGE's ability to generate unlimited-length driving videos. We generated 600 frames of high-quality driving videos on the Nuscenes dataset, which far exceeds the maximum length achievable by existing methods.

cs.CV

Vision-Centric BEV Perception: A Survey

In recent years, vision-centric Bird's Eye View (BEV) perception has garnered significant interest from both industry and academia due to its inherent advantages, such as providing an intuitive representation of the world and being conducive to data fusion. The rapid advancements in deep learning have led to the proposal of numerous methods for addressing vision-centric BEV perception challenges. However, there has been no recent survey encompassing this novel and burgeoning research field. To catalyze future research, this paper presents a comprehensive survey of the latest developments in vision-centric BEV perception and its extensions. It compiles and organizes up-to-date knowledge, offering a systematic review and summary of prevalent algorithms. Additionally, the paper provides in-depth analyses and comparative results on various BEV perception tasks, facilitating the evaluation of future works and sparking new research directions. Furthermore, the paper discusses and shares valuable empirical implementation details to aid in the advancement of related algorithms.

cs.CV

Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild

We present a novel 3D pose refinement approach based on differentiable rendering for objects of arbitrary categories in the wild. In contrast to previous methods, we make two main contributions: First, instead of comparing real-world images and synthetic renderings in the RGB or mask space, we compare them in a feature space optimized for 3D pose refinement. Second, we introduce a novel differentiable renderer that learns to approximate the rasterization backward pass from data instead of relying on a hand-crafted algorithm. For this purpose, we predict deep cross-domain correspondences between RGB images and 3D model renderings in the form of what we call geometric correspondence fields. These correspondence fields serve as pixel-level gradients which are analytically propagated backward through the rendering pipeline to perform a gradient-based optimization directly on the 3D pose. In this way, we precisely align 3D models to objects in RGB images which results in significantly improved 3D pose estimates. We evaluate our approach on the challenging Pix3D dataset and achieve up to 55% relative improvement compared to state-of-the-art refinement methods in multiple metrics.

cs.CV

3D Pose Estimation for Fine-Grained Object Categories

Existing object pose estimation datasets are related to generic object types and there is so far no dataset for fine-grained object categories. In this work, we introduce a new large dataset to benchmark pose estimation for fine-grained objects, thanks to the availability of both 2D and 3D fine-grained data recently. Specifically, we augment two popular fine-grained recognition datasets (StanfordCars and CompCars) by finding a fine-grained 3D CAD model for each sub-category and manually annotating each object in images with 3D pose. We show that, with enough training data, a full perspective model with continuous parameters can be estimated using 2D appearance information alone. We achieve this via a framework based on Faster/Mask R-CNN. This goes beyond previous works on category-level pose estimation, which only estimate discrete/continuous viewpoint angles or recover rotation matrices often with the help of key points. Furthermore, with fine-grained 3D models available, we incorporate a dense 3D representation named as location field into the CNN-based pose estimation framework to further improve the performance. The new dataset is available at www.umiacs.umd.edu/~wym/3dpose.html

cs.CV

Improving Annotation for 3D Pose Dataset of Fine-Grained Object Categories

Existing 3D pose datasets of object categories are limited to generic object types and lack of fine-grained information. In this work, we introduce a new large-scale dataset that consists of 409 fine-grained categories and 31,881 images with accurate 3D pose annotation. Specifically, we augment three existing fine-grained object recognition datasets (StanfordCars, CompCars and FGVC-Aircraft) by finding a specific 3D model for each sub-category from ShapeNet and manually annotating each 2D image by adjusting a full set of 7 continuous perspective parameters. Since the fine-grained shapes allow 3D models to better fit the images, we further improve the annotation quality by initializing from the human annotation and conducting local search of the pose parameters with the objective of maximizing the IoUs between the projected mask and the segmentation reference estimated from state-of-the-art deep Convolutional Neural Networks (CNNs). We provide full statistics of the annotations with qualitative and quantitative comparisons suggesting that our dataset can be a complementary source for studying 3D pose estimation. The dataset can be downloaded at http://users.umiacs.umd.edu/~wym/3dpose.html.

cs.CV

Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition

Compared to earlier multistage frameworks using CNN features, recent end-to-end deep approaches for fine-grained recognition essentially enhance the mid-level learning capability of CNNs. Previous approaches achieve this by introducing an auxiliary network to infuse localization information into the main classification network, or a sophisticated feature encoding method to capture higher order feature statistics. We show that mid-level representation learning can be enhanced within the CNN framework, by learning a bank of convolutional filters that capture class-specific discriminative patches without extra part or bounding box annotations. Such a filter bank is well structured, properly initialized and discriminatively learned through a novel asymmetric multi-stream architecture with convolutional filter supervision and a non-random layer initialization. Experimental results show that our approach achieves state-of-the-art on three publicly available fine-grained recognition datasets (CUB-200-2011, Stanford Cars and FGVC-Aircraft). Ablation studies and visualizations are provided to understand our approach.

cs.CV

Learning Discriminative Features via Label Consistent Neural Network

Deep Convolutional Neural Networks (CNN) enforces supervised information only at the output layer, and hidden layers are trained by back propagating the prediction error from the output layer without explicit supervision. We propose a supervised feature learning approach, Label Consistent Neural Network, which enforces direct supervision in late hidden layers. We associate each neuron in a hidden layer with a particular class label and encourage it to be activated for input signals from the same class. More specifically, we introduce a label consistency regularization called "discriminative representation error" loss for late hidden layers and combine it with classification error loss to build our overall objective function. This label consistency constraint alleviates the common problem of gradient vanishing and tends to faster convergence; it also makes the features derived from late hidden layers discriminative enough for classification even using a simple $k$-NN classifier, since input signals from the same class will have very similar representations. Experimental results demonstrate that our approach achieves state-of-the-art performances on several public benchmarks for action and object category recognition.

cs.CV

Mining Discriminative Triplets of Patches for Fine-Grained Classification

Fine-grained classification involves distinguishing between similar sub-categories based on subtle differences in highly localized regions; therefore, accurate localization of discriminative regions remains a major challenge. We describe a patch-based framework to address this problem. We introduce triplets of patches with geometric constraints to improve the accuracy of patch localization, and automatically mine discriminative geometrically-constrained triplets for classification. The resulting approach only requires object bounding boxes. Its effectiveness is demonstrated using four publicly available fine-grained datasets, on which it outperforms or achieves comparable performance to the state-of-the-art in classification.

cs.CV

Secure Beamforming For MIMO Broadcasting With Wireless Information And Power Transfer

This paper considers a basic MIMO information-energy (I-E) broadcast system, where a multi-antenna transmitter transmits information and energy simultaneously to a multi-antenna information receiver and a dual-functional multi-antenna energy receiver which is also capable of decoding information. Due to the open nature of wireless medium and the dual purpose of information and energy transmission, secure information transmission while ensuring efficient energy harvesting is a critical issue for such a broadcast system. Assuming that physical layer security techniques are applied to the system to ensure secure transmission from the transmitter to the information receiver, we study beamforming design to maximize the achievable secrecy rate subject to a total power constraint and an energy harvesting constraint. First, based on semidefinite relaxation, we propose global optimal solutions to the secrecy rate maximization (SRM) problem in the single-stream case and a specific full-stream case where the difference of Gram matrices of the channel matrices is positive semidefinite. Then, we propose a simple iterative algorithm named inexact block coordinate descent (IBCD) algorithm to tackle the SRM problem of general case with arbitrary number of streams. We proves that the IBCD algorithm can monotonically converge to a Karush-Kuhn-Tucker (KKT) solution to the SRM problem. Furthermore, we extend the IBCD algorithm to the joint beamforming and artificial noise design problem. Finally, simulations are performed to validate the performance of the proposed beamforming algorithms.

cs.IT

Automatic reconstruction of fault networks from seismicity catalogs including location uncertainty

We introduce the Anisotropic Clustering of Location Uncertainty Distributions (ACLUD) method to reconstruct active fault networks on the basis of both earthquake locations and their estimated individual uncertainties. After a massive search through the large solution space of possible reconstructed fault networks, we apply six different validation procedures in order to select the corresponding best fault network. Two of the validation steps (cross-validation and Bayesian Information Criterion (BIC) process the fit residuals, while the four others look for solutions that provide the best agreement with independently observed focal mechanisms. Tests on synthetic catalogs allow us to qualify the performance of the fitting method and of the various validation procedures. The ACLUD method is able to provide solutions that are close to the expected ones, especially for the BIC and focal mechanismbased techniques. The clustering method complemented by the validation step based on focal mechanisms provides good solutions even in the presence of a significant spatial background seismicity rate. Our new fault reconstruction method is then applied to the Landers area in Southern California and compared with previous clustering methods. The results stress the importance of taking into account undersampled sub-fault structures as well as of the spatially inhomogeneous location uncertainties.

physics.geo-ph

Distributed Optimal Rate-Reliability-Lifetime Tradeoff in Wireless Sensor Networks

The transmission rate, delivery reliability and network lifetime are three fundamental but conflicting design objectives in energy-constrained wireless sensor networks. In this paper, we address the optimal rate-reliability-lifetime tradeoff with link capacity constraint, reliability constraint and energy constraint. By introducing the weight parameters, we combine the objectives at rate, reliability, and lifetime into a single objective to characterize the tradeoff among them. However, the optimization formulation of the rate-reliability-reliability tradeoff is neither separable nor convex. Through a series of transformations, a separable and convex problem is derived, and an efficient distributed Subgradient Dual Decomposition algorithm (SDD) is proposed. Numerical examples confirm its convergence. Also, numerical examples investigate the impact of weight parameters on the rate utility, reliability utility and network lifetime, which provide a guidance to properly set the value of weight parameters for a desired performance of WSNs according to the realistic application's requirements.

cs.NI

Quantization Reference Voltage of the Modulated Wideband Converter

The Modulated Wideband Converter (MWC) is a recently proposed analog-to-digital converter (ADC) based on Compressive Sensing (CS) theory. Unlike conventional ADCs, its quantization reference voltage, which is important to the system performance, does not equal the maximum amplitude of original analog signal. In this paper, the quantization reference voltage of the MWC is theoretically analyzed and the conclusion demonstrates that the reference voltage is proportional to the square root of $q$, which is a trade-off parameter between sampling rate and number of channels. Further discussions and simulation results show that the reference voltage is proportional to the square root of $Nq$ when the signal consists of $N$ narrowband signals.

cs.IT