arXiv subjects

Lin Wang

Publications and source records attributed to Lin Wang.

At least 235 records · Page 13Linked to original sources

arXiv2024

CRF360D: Monocular 360 Depth Estimation via Spherical Fully-Connected CRFs

Monocular 360 depth estimation is challenging due to the inherent distortion of the equirectangular projection (ERP). This distortion causes a problem: spherical adjacent points are separated after being projected to the ERP plane, particularly in the polar regions. To tackle this problem, recent methods calculate the spherical neighbors in the tangent domain. However, as the tangent patch and sphere only have one common point, these methods construct neighboring spherical relationships around the common point. In this paper, we propose spherical fully-connected CRFs (SF-CRFs). We begin by evenly partitioning an ERP image with regular windows, where windows at the equator involve broader spherical neighbors than those at the poles. To improve the spherical relationships, our SF-CRFs enjoy two key components. Firstly, to involve sufficient spherical neighbors, we propose a Spherical Window Transform (SWT) module. This module aims to replicate the equator window's spherical relationships to all other windows, leveraging the rotational invariance of the sphere. Remarkably, the transformation process is highly efficient, completing the transformation of all windows in a 512X1024 ERP with 0.038 seconds on CPU. Secondly, we propose a Planar-Spherical Interaction (PSI) module to facilitate the relationships between regular and transformed windows, which not only preserves the local details but also captures global structures. By building a decoder based on the SF-CRFs blocks, we propose CRF360D, a novel 360 depth estimation framework that achieves state-of-the-art performance across diverse datasets. Our CRF360D is compatible with different perspective image-trained backbones (e.g., EfficientNet), serving as the encoder.

cs.CV↗

arXiv2024

Characterizing Regional Importance in Cities with Human Mobility Motifs in Metro Networks

Uncovering higher-order spatiotemporal dependencies within human mobility networks offers valuable insights into the analysis of urban structures. In most existing studies, human mobility networks are typically constructed by aggregating all trips without distinguishing who takes which specific trip. Instead, we claim individual mobility motifs, higher-order structures generated by daily trips of people, as fundamental units of human mobility networks. In this paper, we propose two network construction frameworks at the level of mobility motifs in characterizing regional importance in cities. Firstly, we enhance the structural dependencies within mobility motifs and proceed to construct mobility networks based on the enhanced mobility motifs. Secondly, taking inspiration from PageRank, we speculate that people would allocate values of importance to destinations according to their trip intentions. A motif-wise network construction framework is proposed based on the established mechanism. Leveraging large-scale metro data across cities, we construct three types of human mobility networks and characterize the regional importance by node importance indicators. Our comparison results suggest that the motif-based mobility network outperforms the classic mobility network, thus highlighting the efficacy of the introduced human mobility motifs. Finally, we demonstrate that the performance in characterizing the regional importance is significantly improved by our motif-wise framework.

cs.SI↗

arXiv2024

Learning High-Quality Navigation and Zooming on Omnidirectional Images in Virtual Reality

Viewing omnidirectional images (ODIs) in virtual reality (VR) represents a novel form of media that provides immersive experiences for users to navigate and interact with digital content. Nonetheless, this sense of immersion can be greatly compromised by a blur effect that masks details and hampers the user's ability to engage with objects of interest. In this paper, we present a novel system, called OmniVR, designed to enhance visual clarity during VR navigation. Our system enables users to effortlessly locate and zoom in on the objects of interest in VR. It captures user commands for navigation and zoom, converting these inputs into parameters for the Mobius transformation matrix. Leveraging these parameters, the ODI is refined using a learning-based algorithm. The resultant ODI is presented within the VR media, effectively reducing blur and increasing user engagement. To verify the effectiveness of our system, we first evaluate our algorithm with state-of-the-art methods on public datasets, which achieves the best performance. Furthermore, we undertake a comprehensive user study to evaluate viewer experiences across diverse scenarios and to gather their qualitative feedback from multiple perspectives. The outcomes reveal that our system enhances user engagement by improving the viewers' recognition, reducing discomfort, and improving the overall immersive experience. Our system makes the navigation and zoom more user-friendly.

cs.HC↗

arXiv2024

Integrated Sensing and Communication Channel Modeling: A Survey

Integrated sensing and communication (ISAC) is expected to play a crucial role in the sixth-generation (6G) mobile communication systems, offering potential applications in the scenarios of intelligent transportation, smart factories, etc. The performance of radar sensing in ISAC systems is closely related to the characteristics of radar sensing and communication channels. Therefore, ISAC channel modeling serves as a fundamental cornerstone for evaluating and optimizing ISAC systems. This article provides a comprehensive survey on the ISAC channel modeling methods. Furthermore, the methods of target radar cross section (RCS) modeling and clutter RCS modeling are summarized. Finally, we discuss the future research trends related to ISAC channel modeling in various scenarios.

cs.NI↗

arXiv2024

360SFUDA++: Towards Source-free UDA for Panoramic Segmentation by Learning Reliable Category Prototypes

In this paper, we address the challenging source-free unsupervised domain adaptation (SFUDA) for pinhole-to-panoramic semantic segmentation, given only a pinhole image pre-trained model (i.e., source) and unlabeled panoramic images (i.e., target). Tackling this problem is non-trivial due to three critical challenges: 1) semantic mismatches from the distinct Field-of-View (FoV) between domains, 2) style discrepancies inherent in the UDA problem, and 3) inevitable distortion of the panoramic images. To tackle these problems, we propose 360SFUDA++ that effectively extracts knowledge from the source pinhole model with only unlabeled panoramic images and transfers the reliable knowledge to the target panoramic domain. Specifically, we first utilize Tangent Projection (TP) as it has less distortion and meanwhile slits the equirectangular projection (ERP) to patches with fixed FoV projection (FFP) to mimic the pinhole images. Both projections are shown effective in extracting knowledge from the source model. However, as the distinct projections make it less possible to directly transfer knowledge between domains, we then propose Reliable Panoramic Prototype Adaptation Module (RP2AM) to transfer knowledge at both prediction and prototype levels. RP$^2$AM selects the confident knowledge and integrates panoramic prototypes for reliable knowledge adaptation. Moreover, we introduce Cross-projection Dual Attention Module (CDAM), which better aligns the spatial and channel characteristics across projections at the feature level between domains. Both knowledge extraction and transfer processes are synchronously updated to reach the best performance. Extensive experiments on the synthetic and real-world benchmarks, including outdoor and indoor scenarios, demonstrate that our 360SFUDA++ achieves significantly better performance than prior SFUDA methods.

cs.CV↗

arXiv2024

MYCloth: Towards Intelligent and Interactive Online T-Shirt Customization based on User's Preference

In conventional online T-shirt customization, consumers, \ie, users, can achieve the intended design only after repeated adjustments of the design prototypes presented by sellers in online dialogues. However, this process is prone to limited visual feedback and cumbersome communication, thus detracting from users' customization experience and time. This paper presents an intelligent and interactive online customization system, named \textbf{MYCloth}, aiming to enhance the T-shirt customization experience. Given the user's text input, our MYCloth employs ChatGPT to refine the text prompt and generate the intended paint of the cloth via the Stable Diffusion model. Our MYCloth also enables the user to preview the final outcome via a novel learning-based virtual try-on model. The whole system allows to iteratively adjust the cloth till optimal design is achieved. We verify the system's efficacy through a series of performance evaluations and user studies, highlighting its ability to streamline the online customization process and improve overall satisfaction.

cs.HC↗

arXiv2024

Deep Learning Based Multi-Node ISAC 4D Environmental Reconstruction with Uplink- Downlink Cooperation

Utilizing widely distributed communication nodes to achieve environmental reconstruction is one of the significant scenarios for Integrated Sensing and Communication (ISAC) and a crucial technology for 6G. To achieve this crucial functionality, we propose a deep learning based multi-node ISAC 4D environment reconstruction method with Uplink-Downlink (UL-DL) cooperation, which employs virtual aperture technology, Constant False Alarm Rate (CFAR) detection, and Mutiple Signal Classification (MUSIC) algorithm to maximize the sensing capabilities of single sensing nodes. Simultaneously, it introduces a cooperative environmental reconstruction scheme involving multi-node cooperation and Uplink-Downlink (UL-DL) cooperation to overcome the limitations of single-node sensing caused by occlusion and limited viewpoints. Furthermore, the deep learning models Attention Gate Gridding Residual Neural Network (AGGRNN) and Multi-View Sensing Fusion Network (MVSFNet) to enhance the density of sparsely reconstructed point clouds are proposed, aiming to restore as many original environmental details as possible while preserving the spatial structure of the point cloud. Additionally, we propose a multi-level fusion strategy incorporating both data-level and feature-level fusion to fully leverage the advantages of multi-node cooperation. Experimental results demonstrate that the environmental reconstruction performance of this method significantly outperforms other comparative method, enabling high-precision environmental reconstruction using ISAC system.

eess.SP↗

arXiv2024

Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling

Mobile and IoT applications increasingly adopt deep learning inference to provide intelligence. Inference requests are typically sent to a cloud infrastructure over a wireless network that is highly variable, leading to the challenge of dynamic Service Level Objectives (SLOs) at the request level. This paper presents Sponge, a novel deep learning inference serving system that maximizes resource efficiency while guaranteeing dynamic SLOs. Sponge achieves its goal by applying in-place vertical scaling, dynamic batching, and request reordering. Specifically, we introduce an Integer Programming formulation to capture the resource allocation problem, providing a mathematical model of the relationship between latency, batch size, and resources. We demonstrate the potential of Sponge through a prototype implementation and preliminary experiments and discuss future works.

cs.DC↗

arXiv2024

Integrated Sensing and Communication enabled Multiple Base Stations Cooperative UAV Detection

Integrated sensing and communication (ISAC) exhibits notable potential for sensing the unmanned aerial vehicles (UAVs), facilitating real-time monitoring of UAVs for security insurance. Due to the low sensing accuracy of single base stations (BSs), a cooperative UAV sensing method by multi-BS is proposed in this paper to achieve high-accuracy sensing. Specifically, a multiple signal classification (MUSIC)-based symbol-level fusion method is proposed for UAV localization and velocity estimation, consisting of a single-BS preprocessing step and a lattice points searching step. The preprocessing procedure enhances the single-BS accuracy by superposing multiple spectral functions, thereby establishing a reference value for subsequent lattice points searching. Furthermore, the lattice point with minimal error compared to the preprocessing results is determined as the fusion result. Extensive simulation results reveal that the proposed symbol-level fusion method outperforms the benchmarking methods in localization and velocity estimation.

eess.SP↗

arXiv2024

AntDT: A Self-Adaptive Distributed Training Framework for Leader and Straggler Nodes

Many distributed training techniques like Parameter Server and AllReduce have been proposed to take advantage of the increasingly large data and rich features. However, stragglers frequently occur in distributed training due to resource contention and hardware heterogeneity, which significantly hampers the training efficiency. Previous works only address part of the stragglers and could not adaptively solve various stragglers in practice. Additionally, it is challenging to use a systematic framework to address all stragglers because different stragglers require diverse data allocation and fault-tolerance mechanisms. Therefore, this paper proposes a unified distributed training framework called AntDT (Ant Distributed Training Framework) to adaptively solve the straggler problems. Firstly, the framework consists of four components, including the Stateful Dynamic Data Sharding service, Monitor, Controller, and Agent. These components work collaboratively to efficiently distribute workloads and provide a range of pre-defined straggler mitigation methods with fault tolerance, thereby hiding messy details of data allocation and fault handling. Secondly, the framework provides a high degree of flexibility, allowing for the customization of straggler mitigation solutions based on the specific circumstances of the cluster. Leveraging this flexibility, we introduce two straggler mitigation solutions, namely AntDT-ND for non-dedicated clusters and AntDT-DD for dedicated clusters, as practical examples to resolve various types of stragglers at Ant Group. Justified by our comprehensive experiments and industrial deployment statistics, AntDT outperforms other SOTA methods more than 3x in terms of training efficiency. Additionally, in Alipay's homepage recommendation scenario, using AntDT reduces the training duration of the ranking model from 27.8 hours to just 5.4 hours.

cs.DC↗

arXiv2024

AntBatchInfer: Elastic Batch Inference in the Kubernetes Cluster

Offline batch inference is a common task in the industry for deep learning applications, but it can be challenging to ensure stability and performance when dealing with large amounts of data and complicated inference pipelines. This paper demonstrated AntBatchInfer, an elastic batch inference framework, which is specially optimized for the non-dedicated cluster. AntBatchInfer addresses these challenges by providing multi-level fault-tolerant capabilities, enabling the stable execution of versatile and long-running inference tasks. It also improves inference efficiency by pipelining, intra-node, and inter-node scaling. It further optimizes the performance in complicated multiple-model batch inference scenarios. Through extensive experiments and real-world statistics, we demonstrate the superiority of our framework in terms of stability and efficiency. In the experiment, it outperforms the baseline by at least $2\times$ and $6\times$ in the single-model or multiple-model batch inference. Also, it is widely used at Ant Group, with thousands of daily jobs from various scenarios, including DLRM, CV, and NLP, which proves its practicability in the industry.

cs.LG↗

arXiv2024

Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks

Event cameras are bio-inspired sensors that capture the per-pixel intensity changes asynchronously and produce event streams encoding the time, pixel position, and polarity (sign) of the intensity changes. Event cameras possess a myriad of advantages over canonical frame-based cameras, such as high temporal resolution, high dynamic range, low latency, etc. Being capable of capturing information in challenging visual conditions, event cameras have the potential to overcome the limitations of frame-based cameras in the computer vision and robotics community. In very recent years, deep learning (DL) has been brought to this emerging field and inspired active research endeavors in mining its potential. However, there is still a lack of taxonomies in DL techniques for event-based vision. We first scrutinize the typical event representations with quality enhancement methods as they play a pivotal role as inputs to the DL models. We then provide a comprehensive survey of existing DL-based methods by structurally grouping them into two major categories: 1) image/video reconstruction and restoration; 2) event-based scene understanding and 3D vision. We conduct benchmark experiments for the existing methods in some representative research directions, i.e., image reconstruction, deblurring, and object recognition, to identify some critical insights and problems. Finally, we have discussions regarding the challenges and provide new perspectives for inspiring more research studies.

cs.CV↗

arXiv2024

Unsupervised Visible-Infrared ReID via Pseudo-label Correction and Modality-level Alignment

Unsupervised visible-infrared person re-identification (UVI-ReID) has recently gained great attention due to its potential for enhancing human detection in diverse environments without labeling. Previous methods utilize intra-modality clustering and cross-modality feature matching to achieve UVI-ReID. However, there exist two challenges: 1) noisy pseudo labels might be generated in the clustering process, and 2) the cross-modality feature alignment via matching the marginal distribution of visible and infrared modalities may misalign the different identities from two modalities. In this paper, we first conduct a theoretic analysis where an interpretable generalization upper bound is introduced. Based on the analysis, we then propose a novel unsupervised cross-modality person re-identification framework (PRAISE). Specifically, to address the first challenge, we propose a pseudo-label correction strategy that utilizes a Beta Mixture Model to predict the probability of mis-clustering based network's memory effect and rectifies the correspondence by adding a perceptual term to contrastive learning. Next, we introduce a modality-level alignment strategy that generates paired visible-infrared latent features and reduces the modality gap by aligning the labeling function of visible and infrared features to learn identity discriminative and modality-invariant features. Experimental results on two benchmark datasets demonstrate that our method achieves state-of-the-art performance than the unsupervised visible-ReID methods.

cs.CV↗

arXiv2024

Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach

Event camera has recently received much attention for low-light image enhancement (LIE) thanks to their distinct advantages, such as high dynamic range. However, current research is prohibitively restricted by the lack of large-scale, real-world, and spatial-temporally aligned event-image datasets. To this end, we propose a real-world (indoor and outdoor) dataset comprising over 30K pairs of images and events under both low and normal illumination conditions. To achieve this, we utilize a robotic arm that traces a consistent non-linear trajectory to curate the dataset with spatial alignment precision under 0.03mm. We then introduce a matching alignment strategy, rendering 90% of our dataset with errors less than 0.01s. Based on the dataset, we propose a novel event-guided LIE approach, called EvLight, towards robust performance in real-world low-light scenes. Specifically, we first design the multi-scale holistic fusion branch to extract holistic structural and textural information from both events and images. To ensure robustness against variations in the regional illumination and noise, we then introduce a Signal-to-Noise-Ratio (SNR)-guided regional feature selection to selectively fuse features of images from regions with high SNR and enhance those with low SNR by extracting regional structure information from events. Extensive experiments on our dataset and the synthetic SDSD dataset demonstrate our EvLight significantly surpasses the frame-based methods. Code and datasets are available at https://vlislab22.github.io/eg-lowlight/.

cs.CV↗

arXiv2024

Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM

Implicit neural representation (INR), in combination with geometric rendering, has recently been employed in real-time dense RGB-D SLAM. Despite active research endeavors being made, there lacks a unified protocol for fair evaluation, impeding the evolution of this area. In this work, we establish, to our knowledge, the first open-source benchmark framework to evaluate the performance of a wide spectrum of commonly used INRs and rendering functions for mapping and localization. The goal of our benchmark is to 1) gain an intuition of how different INRs and rendering functions impact mapping and localization and 2) establish a unified evaluation protocol w.r.t. the design choices that may impact the mapping and localization. With the framework, we conduct a large suite of experiments, offering various insights in choosing the INRs and geometric rendering functions: for example, the dense feature grid outperforms other INRs (e.g. tri-plane and hash grid), even when geometric and color features are jointly encoded for memory efficiency. To extend the findings into the practical scenario, a hybrid encoding strategy is proposed to bring the best of the accuracy and completion from the grid-based and decomposition-based INRs. We further propose explicit hybrid encoding for high-fidelity dense grid mapping to comply with the RGB-D SLAM system that puts the premise on robustness and computation efficiency.

cs.CV↗

arXiv2024

GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation

This paper tackles a novel yet challenging problem: how to transfer knowledge from the emerging Segment Anything Model (SAM) -- which reveals impressive zero-shot instance segmentation capacity -- to learn a compact panoramic semantic segmentation model, i.e., student, without requiring any labeled data. This poses considerable challenges due to SAM's inability to provide semantic labels and the large capacity gap between SAM and the student. To this end, we propose a novel framework, called GoodSAM, that introduces a teacher assistant (TA) to provide semantic information, integrated with SAM to generate ensemble logits to achieve knowledge transfer. Specifically, we propose a Distortion-Aware Rectification (DAR) module that first addresses the distortion problem of panoramic images by imposing prediction-level consistency and boundary enhancement. This subtly enhances TA's prediction capacity on panoramic images. DAR then incorporates a cross-task complementary fusion block to adaptively merge the predictions of SAM and TA to obtain more reliable ensemble logits. Moreover, we introduce a Multi-level Knowledge Adaptation (MKA) module to efficiently transfer the multi-level feature knowledge from TA and ensemble logits to learn a compact student model. Extensive experiments on two benchmarks show that our GoodSAM achieves a remarkable +3.75\% mIoU improvement over the state-of-the-art (SOTA) domain adaptation methods. Also, our most lightweight model achieves comparable performance to the SOTA methods with only 3.7M parameters.

cs.CV↗

arXiv2024

Interference Management for Integrated Sensing and Communication Systems: A Survey

Emerging applications such as autonomous driving and Internet of things (IoT) services put forward the demand for simutaneous sensing and communication functions in the same system. Integrated sensing and communication (ISAC) has the potential to meet the demands of ubiquitous communication and high-precision sensing due to the advantages of spectrum and hardware resource sharing, as well as the mutual enhancement of sensing and communication. However, ISAC system faces severe interference requiring effective interference suppression, avoidance, and exploitation techniques. This article provides a comprehensive survey on the interference management techniques in ISAC systems, involving network architecture, system design, signal processing, and resource allocation. We first review the channel modeling and performance metrics of the ISAC system. Then, the methods for managing self-interference (SI), mutual interference (MI), and clutter in a single base station (BS) system are summarized, including interference suppression, interference avoidance and interference exploitation methods. Furthermore, cooperative interference management methods are studied to address the cross-link interference (CLI) in a coordinated multipoint ISAC (CoMP-ISAC) system. Finally, future trends are revealed. This article may provide a reference for the study of interference management in ISAC systems.

cs.NI↗

arXiv2024

Semantics, Distortion, and Style Matter: Towards Source-free UDA for Panoramic Segmentation

This paper addresses an interesting yet challenging problem -- source-free unsupervised domain adaptation (SFUDA) for pinhole-to-panoramic semantic segmentation -- given only a pinhole image-trained model (i.e., source) and unlabeled panoramic images (i.e., target). Tackling this problem is nontrivial due to the semantic mismatches, style discrepancies, and inevitable distortion of panoramic images. To this end, we propose a novel method that utilizes Tangent Projection (TP) as it has less distortion and meanwhile slits the equirectangular projection (ERP) with a fixed FoV to mimic the pinhole images. Both projections are shown effective in extracting knowledge from the source model. However, the distinct projection discrepancies between source and target domains impede the direct knowledge transfer; thus, we propose a panoramic prototype adaptation module (PPAM) to integrate panoramic prototypes from the extracted knowledge for adaptation. We then impose the loss constraints on both predictions and prototypes and propose a cross-dual attention module (CDAM) at the feature level to better align the spatial and channel characteristics across the domains and projections. Both knowledge extraction and transfer processes are synchronously updated to reach the best performance. Extensive experiments on the synthetic and real-world benchmarks, including outdoor and indoor scenarios, demonstrate that our method achieves significantly better performance than prior SFUDA methods for pinhole-to-panoramic adaptation.

cs.CV↗