arXiv subjects

Peng Wang

Publications and source records attributed to Peng Wang.

At least 667 records · Page 37Linked to original sources

arXiv2022

SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views

We introduce SparseNeuS, a novel neural rendering based method for the task of surface reconstruction from multi-view images. This task becomes more difficult when only sparse images are provided as input, a scenario where existing neural reconstruction approaches usually produce incomplete or distorted results. Moreover, their inability of generalizing to unseen new scenes impedes their application in practice. Contrarily, SparseNeuS can generalize to new scenes and work well with sparse images (as few as 2 or 3). SparseNeuS adopts signed distance function (SDF) as the surface representation, and learns generalizable priors from image features by introducing geometry encoding volumes for generic surface prediction. Moreover, several strategies are introduced to effectively leverage sparse views for high-quality reconstruction, including 1) a multi-level geometry reasoning framework to recover the surfaces in a coarse-to-fine manner; 2) a multi-scale color blending scheme for more reliable color prediction; 3) a consistency-aware fine-tuning scheme to control the inconsistent regions caused by occlusion and noise. Extensive experiments demonstrate that our approach not only outperforms the state-of-the-art methods, but also exhibits good efficiency, generalizability, and flexibility.

cs.CV↗

arXiv2022

Robust Security Analysis Based on Random Geometry Theory for Satellite-Terrestrial-Vehicle Network

Driven by B5G and 6G technologies, multi-network fusion is an indispensable tendency for future communications. In this paper, we focus on and analyze the \emph{security performance} (SP) of the \emph{satellite-terrestrial downlink transmission} (STDT). Here, the STDT is composed of a satellite network and a vehicular network with a legitimate mobile receiver and an mobile eavesdropper distributing. To theoretically analyze the SP of this system from the perspective of mobile terminals better, the random geometry theory is adopted, which assumes that both terrestrial vehicles are distributed stochastically in one beam of the satellite. Furthermore, based on this theory, the closed-form analytical expressions for two crucial and specific indicators in the STDT are derived, respectively, the secrecy outage probability and the ergodic secrecy capacity. Additionally, several related variables restricting the SP of the STDT are discussed, and specific schemes are presented to enhance the SP. Then, the asymptotic property is investigated in the high signal-to-noise ratio scenario, and accurate and asymptotic closed-form expressions are given. Finally, simulation results show that, under the precondition of guaranteeing the reliability of the STDT, the asymptotic solutions outperform the corresponding accurate results significantly in the effectiveness.

cs.IT↗

arXiv2022

Progressively-connected Light Field Network for Efficient View Synthesis

This paper presents a Progressively-connected Light Field network (ProLiF), for the novel view synthesis of complex forward-facing scenes. ProLiF encodes a 4D light field, which allows rendering a large batch of rays in one training step for image- or patch-level losses. Directly learning a neural light field from images has difficulty in rendering multi-view consistent images due to its unawareness of the underlying 3D geometry. To address this problem, we propose a progressive training scheme and regularization losses to infer the underlying geometry during training, both of which enforce the multi-view consistency and thus greatly improves the rendering quality. Experiments demonstrate that our method is able to achieve significantly better rendering quality than the vanilla neural light fields and comparable results to NeRF-like rendering methods on the challenging LLFF dataset and Shiny Object dataset. Moreover, we demonstrate better compatibility with LPIPS loss to achieve robustness to varying light conditions and CLIP loss to control the rendering style of the scene. Project page: https://totoro97.github.io/projects/prolif.

cs.CV↗

arXiv2022

Appearance of an Infalling Star in Black Holes with Multiple Photon Spheres

Photon spheres play a pivotal role in the imaging of luminous objects near black holes. In this paper, we examine observational appearances of a star freely falling in hairy black holes, which can possess one or two photon spheres outside the event horizon. When there exists a single photon sphere, the total luminosity measured by distant observers decreases exponentially with time at late times. Due to successive arrivals of photons orbiting around the photon sphere different times, a specific observer would see a series of light flashes with decreasing intensity, which share a similar frequency content. Whereas in the case with two photon spheres, photons temporarily trapped between the photon spheres can cause a peak of the total luminosity, which is followed by a slow exponential decay, at late times. In addition, these photons lead to one more series of light flashes seen by the specific observer.

gr-qc↗

arXiv2022

Fast-Spanning Ant Colony Optimisation (FaSACO) for Mobile Robot Coverage Path Planning

Coverage Path Planning (CPP) aims at finding an optimal path that covers the whole given space. Due to the NP-hard nature, CPP remains a challenging problem. Bio-inspired algorithms such as Ant Colony Optimisation (ACO) have been exploited to solve the problem because they can utilise heuristic information to mitigate the path planning complexity. This paper proposes the Fast-Spanning Ant Colony Optimisation (FaSACO), where ants can explore the environment with various velocities. By doing so, ants with higher velocities can find destinations or obstacles faster and keep lower velocity ants informed by communicating such information via pheromone trails on the path. This mechanism ensures that the (sub-)~optimal path is found while reducing the overall path planning time. Experimental results show that FaSACO is $19.3-32.3\%$ more efficient than ACO in terms of CPU time, and re-covers $6.9-12.5\%$ less cells than ACO. This makes FaSACO appealing in real-time and energy-limited applications.

cs.RO↗

arXiv2022

Convergence and Recovery Guarantees of the K-Subspaces Method for Subspace Clustering

The K-subspaces (KSS) method is a generalization of the K-means method for subspace clustering. In this work, we present local convergence analysis and a recovery guarantee for KSS, assuming data are generated by the semi-random union of subspaces model, where $N$ points are randomly sampled from $K \ge 2$ overlapping subspaces. We show that if the initial assignment of the KSS method lies within a neighborhood of a true clustering, it converges at a superlinear rate and finds the correct clustering within $Θ(\log\log N)$ iterations with high probability. Moreover, we propose a thresholding inner-product based spectral method for initialization and prove that it produces a point in this neighborhood. We also present numerical results of the studied method to support our theoretical developments.

math.OC↗

arXiv2022

Repro Samples Method for Finite- and Large-Sample Inferences

This article presents a novel, general, and effective simulation-inspired approach, called {\it repro samples method}, to conduct statistical inference. The approach studies the performance of artificial samples, referred to as {\it repro samples}, obtained by mimicking the true observed sample to achieve uncertainty quantification and construct confidence sets for parameters of interest with guaranteed coverage rates. Both exact and asymptotic inferences are developed. An attractive feature of the general framework developed is that it does not rely on the large sample central limit theorem and is likelihood-free. As such, it is thus effective for complicated inference problems which we can not solve using the large sample central limit theorem. The proposed method is applicable to a wide range of problems, including many open questions where solutions were previously unavailable, for example, those involving discrete or non-numerical parameters. To reduce the large computational cost of such inference problems, we develop a unique matching scheme to obtain a data-driven candidate set. Moreover, we show the advantages of the proposed framework over the classical Neyman-Pearson framework. We demonstrate the effectiveness of the proposed approach on various models throughout the paper and provide a case study that addresses an open inference question on how to quantify the uncertainty for the unknown number of components in a normal mixture model. To evaluate the empirical performance of our repro samples method, we conduct simulations and study real data examples with comparisons to existing approaches. Although the development pertains to the settings where the large sample central limit theorem does not apply, it also has direct extensions to the cases where the central limit theorem does hold.

stat.ME↗

arXiv2022

OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task Comprehensiveness. OFA unifies a diverse set of cross-modal and unimodal tasks, including image generation, visual grounding, image captioning, image classification, language modeling, etc., in a simple sequence-to-sequence learning framework. OFA follows the instruction-based learning in both pretraining and finetuning stages, requiring no extra task-specific layers for downstream tasks. In comparison with the recent state-of-the-art vision & language models that rely on extremely large cross-modal datasets, OFA is pretrained on only 20M publicly available image-text pairs. Despite its simplicity and relatively small-scale training data, OFA achieves new SOTAs in a series of cross-modal tasks while attaining highly competitive performances on uni-modal tasks. Our further analysis indicates that OFA can also effectively transfer to unseen tasks and unseen domains. Our code and models are publicly available at https://github.com/OFA-Sys/OFA.

cs.CV↗

arXiv2022

Effects of Born-Infeld electrodynamics on black hole shadows

In this work, we study the shadow of Born-Infeld (BI) black holes with magnetic monopoles and Schwarzschild black holes immersed in the BI uniform magnetic field. Illuminated by a celestial sphere, black hole images are obtained by using the backward ray-tracing method. For magnetically charged BI black holes, we find that the shadow radius increases with the increase of nonlinear electromagnetics effects. For Schwarzschild black holes immersed in the BI uniform magnetic field, photons tend to move towards the axis of symmetric, resulting in stretched shadows along the equatorial plane.

gr-qc↗

arXiv2022

Probing Phase Structure of Black Holes with Lyapunov Exponents

We conjecture that there exists a relationship between Lyapunov exponents and black hole phase transitions. To support our conjecture, Lyapunov exponents of the motion of particles and ring strings are calculated for Reissner-Nordström-AdS black holes. When a phase transition occurs, the Lyapunov exponents become multivalued, and branches of the Lyapunov exponents coincide with black hole phases. Moreover, the discontinuous change in the Lyapunov exponents can be treated as an order parameter, and has a critical exponent of $1/2$ near the critical point. Our findings reveal that Lyapunov exponents can be an efficient tool to study phase structure of black holes.

gr-qc↗

arXiv2022

End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding

Natural language spatial video grounding aims to detect the relevant objects in video frames with descriptive sentences as the query. In spite of the great advances, most existing methods rely on dense video frame annotations, which require a tremendous amount of human effort. To achieve effective grounding under a limited annotation budget, we investigate one-shot video grounding, and learn to ground natural language in all video frames with solely one frame labeled, in an end-to-end manner. One major challenge of end-to-end one-shot video grounding is the existence of videos frames that are either irrelevant to the language query or the labeled frames. Another challenge relates to the limited supervision, which might result in ineffective representation learning. To address these challenges, we designed an end-to-end model via Information Tree for One-Shot video grounding (IT-OS). Its key module, the information tree, can eliminate the interference of irrelevant frames based on branch search and branch cropping techniques. In addition, several self-supervised tasks are proposed based on the information tree to improve the representation learning under insufficient labeling. Experiments on the benchmark dataset demonstrate the effectiveness of our model.

cs.CV↗

arXiv2022

Pushing the Performance Limit of Scene Text Recognizer without Human Annotation

Scene text recognition (STR) attracts much attention over the years because of its wide application. Most methods train STR model in a fully supervised manner which requires large amounts of labeled data. Although synthetic data contributes a lot to STR, it suffers from the real-tosynthetic domain gap that restricts model performance. In this work, we aim to boost STR models by leveraging both synthetic data and the numerous real unlabeled images, exempting human annotation cost thoroughly. A robust consistency regularization based semi-supervised framework is proposed for STR, which can effectively solve the instability issue due to domain inconsistency between synthetic and real images. A character-level consistency regularization is designed to mitigate the misalignment between characters in sequence recognition. Extensive experiments on standard text recognition benchmarks demonstrate the effectiveness of the proposed method. It can steadily improve existing STR models, and boost an STR model to achieve new state-of-the-art results. To our best knowledge, this is the first consistency regularization based framework that applies successfully to STR.

cs.CV↗

arXiv2022

FastRE: Towards Fast Relation Extraction with Convolutional Encoder and Improved Cascade Binary Tagging Framework

Recent work for extracting relations from texts has achieved excellent performance. However, most existing methods pay less attention to the efficiency, making it still challenging to quickly extract relations from massive or streaming text data in realistic scenarios. The main efficiency bottleneck is that these methods use a Transformer-based pre-trained language model for encoding, which heavily affects the training speed and inference speed. To address this issue, we propose a fast relation extraction model (FastRE) based on convolutional encoder and improved cascade binary tagging framework. Compared to previous work, FastRE employs several innovations to improve efficiency while also keeping promising performance. Concretely, FastRE adopts a novel convolutional encoder architecture combined with dilated convolution, gated unit and residual connection, which significantly reduces the computation cost of training and inference, while maintaining the satisfactory performance. Moreover, to improve the cascade binary tagging framework, FastRE first introduces a type-relation mapping mechanism to accelerate tagging efficiency and alleviate relation redundancy, and then utilizes a position-dependent adaptive thresholding strategy to obtain higher tagging accuracy and better model generalization. Experimental results demonstrate that FastRE is well balanced between efficiency and performance, and achieves 3-10x training speed, 7-15x inference speed faster, and 1/100 parameters compared to the state-of-the-art models, while the performance is still competitive.

cs.CL↗

arXiv2022

Connections between reflected entropies and hyperbolic string vertices

In this paper, we establish connections between reflected entropies of multipartite mixed states in CFT$_{2}$ and hyperbolic string vertices of closed string field theory (CSFT). We show that the reflected surfaces, which are bulk duals of the reflected entropies, share the same Riemann surfaces with the hyperbolic string vertices. This observation enables us to build quantitative relations between the reflected entropies and hyperbolic string vertices. We illustrate the connections with several examples. Consequently, we propose that spacetime structure could be directly generated from the hyperbolic string vertices. The advantage of the hyperbolic string vertices approach is that we have a dynamical equation, the Batalin-Vilkoviski master equation, to control the generating process.

hep-th↗

arXiv2022

Balanced control between performance and saturation for constrained nonlinear systems

This paper addresses the balanced control between performance and saturation for a class of constrained nonlinear systems, including the branches: balanced command filtered backstepping (BCFB) and balanced performance control (BPC). To balance the interconnection and conflict between performance and saturation constraints, define a performance safety evaluation (PSE) function, which evaluates the system safety under the destabilizing effect variables (DEVs) like saturation quantity and filter errors, then the cumulative effects of DEVs are fully utilized and compensated for the performance recovery. Specifically, there exists some degree of tolerance for the DEVs in the safety region, and the compensation operation works when the evaluation of the system goes dangerous. The advantages of the proposed methodology are illustrated in the numerical simulation.

eess.SY↗

arXiv2022

Attract me to Buy: Advertisement Copywriting Generation with Multimodal Multi-structured Information

Recently, online shopping has gradually become a common way of shopping for people all over the world. Wonderful merchandise advertisements often attract more people to buy. These advertisements properly integrate multimodal multi-structured information of commodities, such as visual spatial information and fine-grained structure information. However, traditional multimodal text generation focuses on the conventional description of what existed and happened, which does not match the requirement of advertisement copywriting in the real world. Because advertisement copywriting has a vivid language style and higher requirements of faithfulness. Unfortunately, there is a lack of reusable evaluation frameworks and a scarcity of datasets. Therefore, we present a dataset, E-MMAD (e-commercial multimodal multi-structured advertisement copywriting), which requires, and supports much more detailed information in text generation. Noticeably, it is one of the largest video captioning datasets in this field. Accordingly, we propose a baseline method and faithfulness evaluation metric on the strength of structured information reasoning to solve the demand in reality on this dataset. It surpasses the previous methods by a large margin on all metrics. The dataset and method are coming soon on \url{https://e-mmad.github.io/e-mmad.net/index.html}.

cs.CL↗

arXiv2022

Gravitational Lensing by Black Holes with Multiple Photon Spheres

We study gravitational lensing of light by hairy black holes, which, in a certain parameter regime, can possess two photon spheres of different size outside the event horizon. In particular, we focus on higher-order images of a point-like light source and a luminous celestial sphere produced by strong gravitational lensing near photon spheres. Two photon spheres usually triple the number of high-order images of a point-like light source. When a hairy black hole is illuminated by a celestial sphere, two photon spheres would give rise to two critical curves in the black hole image, and the smaller critical curve coincides with the shadow edge. In addition to a set of higher-order images of the celestial sphere outside the shadow edge, two more sets of higher-order images are observed inside and outside the larger critical curve, respectively.

gr-qc↗

arXiv2022

Dual-Level Decoupled Transformer for Video Captioning

Video captioning aims to understand the spatio-temporal semantic concept of the video and generate descriptive sentences. The de-facto approach to this task dictates a text generator to learn from \textit{offline-extracted} motion or appearance features from \textit{pre-trained} vision models. However, these methods may suffer from the so-called \textbf{\textit{"couple"}} drawbacks on both \textit{video spatio-temporal representation} and \textit{sentence generation}. For the former, \textbf{\textit{"couple"}} means learning spatio-temporal representation in a single model(3DCNN), resulting the problems named \emph{disconnection in task/pre-train domain} and \emph{hard for end-to-end training}. As for the latter, \textbf{\textit{"couple"}} means treating the generation of visual semantic and syntax-related words equally. To this end, we present $\mathcal{D}^{2}$ - a dual-level decoupled transformer pipeline to solve the above drawbacks: \emph{(i)} for video spatio-temporal representation, we decouple the process of it into "first-spatial-then-temporal" paradigm, releasing the potential of using dedicated model(\textit{e.g.} image-text pre-training) to connect the pre-training and downstream tasks, and makes the entire model end-to-end trainable. \emph{(ii)} for sentence generation, we propose \emph{Syntax-Aware Decoder} to dynamically measure the contribution of visual semantic and syntax-related words. Extensive experiments on three widely-used benchmarks (MSVD, MSR-VTT and VATEX) have shown great potential of the proposed $\mathcal{D}^{2}$ and surpassed the previous methods by a large margin in the task of video captioning.

cs.CV↗