JWJingyi Wang

Jingyi Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jingyi Wang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • PDRF-Net: progressive blind registration–fusion for unregistered hyperspectral image with physics consistent spatial spectral decoupling

    by Baiyang Hu, Xiaodian Zhang, Kun Gao, Wenhao Hu, Jiyuan Yang, Yao Huang, Zhijia Yang, Zefeng Zhang, Jingyi Wang

  • An adaptive modulation network for semi-dense infrared and visible image matching

    by Zhijia Yang, Kun Gao, Zefeng Zhang, Jingyi Wang, Wenhao Hu, Yunpeng Feng, Haobo Cheng

  • Hypervision: An on-chip hyperspectral microsystem for online video-rate computational imaging

    by Liheng Bian, Qinghao Meng, Lianjie Li, Zhen Wang, Yibo Feng, Xuan Peng, Jiajun Zhao, Jingyi Wang, Zhu Yang, Jun Zhang

    In this work, we tackled the long-standing challenge of the massive computation for hyperspectral imaging that is required to reconstruct and process large-volume spatial-spectral data cubes. Specifically, we designed a hardware accelerator, fabricated as a neural processing unit (NPU) capable of 9.3 tera operations per second at 16-bit integer (INT16), alongside a topology-aware structured pruning strategy for a lightweight reconstruction network. Through integration with our HyperspecI sensor, we demonstrate a fully standalone visible–near-infrared hyperspectral microsystem (~950 grams) that requires neither external power nor computing resources. The microsystem achieved real-time hyperspectral imaging at 32.9 frames per second (512×512, 61 channels) or 24.6 frames per second (1024×1024, 16 channels) and consumed only ~25.3 watts (367 giga–operations per second per watt). Application demonstrations in intelligent driving and air-to-ground monitoring highlight its practical potential advancing computational hyperspectral imaging from offline processing to integrated online perception.


  • Open Access

    PDRF-Net: Progressive Blind Registration–Fusion for Unregistered Hyperspectral Image with Physics Consistent Spatial Spectral Decoupling

    by Baiyang Hu, Kun Gao, Xiaodian Zhang, Wenhao Hu, Jiyuan Yang, Yao Huang, Zhijia Yang, Zefeng Zhang, Jingyi Wang

    Existing hyperspectral image (HSI) fusion methods typically assume well-registered image pairs, whereas real HSI and multispectral image (MSI) observations often contain rigid offsets, non-rigid deformations, and field-of-view discrepancy. Such discrepancies cause inconsistent spatial-spectral support between aggregated HSI and local MSI, leading to severe spatial–spectral mixing during fusion. To address this issue, we propose PDRF-Net, a physics-consistent progressive blind registration–fusion framework for high-resolution hyperspectral reconstruction from unregistered image pairs. PDRF-Net progressively proceeds from observation-consistent degradation prior recovery to decoupled reconstruction and refinement. Specifically, the Prior Registration–Fusion Degradation Co-optimization Module (PRE) jointly estimates rigid/non-rigid distortions and point spread function (PSF) / spectral response function (SRF) degradations to recover physically consistent priors that more completely characterize the cross-modal degradation process and explicitly relate spatially aggregated HSI observations to MSI measurements. The Spectral-Guided Unmixing Fusion (SGHF) reuses these priors to constrain abundance reconstruction and perform degradation-consistent endmember–abundance-based decoupled fusion, thereby avoiding strict pixelwise correspondence and reducing spatial–spectral mixing distortion caused by residual misalignment. The Spatial Conditioning Refinement Module (SFHR) adaptively refines spatial consistency while balancing spectral fidelity. Extensive experiments on multiple benchmarks demonstrate that PDRF-Net achieves state-of-the-art results under diverse simulated misalignments and scales, and produces higher-quality results with higher Quality with No Reference (QNR) scores on real unregistered data. The code will be released at \url{https://github.com/Gao-Kun-Lab/

  • DSFuse: A Dual-Diffusion Structure for Feature Fidelity Infrared and Visible Image Fusion

    by Zhijia Yang, Kun Gao, Yanzheng Zhang, Xiaodian Zhang, Zibo Hu, Junwei Wang, Jingyi Wang, Wei Li

    Image fusion aims to combine the complementary features of different modalities to produce an informative fused image. Due to the different imaging mechanisms, information conflicts may arise from infrared and visible source images. Existing infrared and visible fusion methods are devoted to preserving the features of source images as much as possible. However, handling conflicting information is often overlooked. Thus, we leverage the powerful generative priors of diffusion and propose a dual-diffusion structure, termed DSFuse, to handle conflicting information and achieve feature fidelity during image fusion processing. Diffusion modules are introduced to guide the fusion network to understand the meaningful information of the source image easily. First, the fusion network is used to retain features in the fused image as much as possible. Then, diffusion modules are used to reconstruct source images from noise based on the output of the fusion network. Finally, feedback from the diffusion modules forces the fusion network to aggregate modality information to ensure fidelity; the high quality of the fusion result is also profitable for a better reconstruction of diffusion modules, forming a positive feedback loop. In addition, we release a new dataset for infrared/visible fusion to support the fusion network training and evaluation, named the multiscene infrared and visible (MSIV) images dataset. Extensive experiments demonstrate that DSFuse outperforms other state-of-the-art (SOTA) fusion methods.


  • Open Access

    Enhanced Grounding DINO: Efficient Cross-Modality Block for Open-Set Object Detection in Remote Sensing

    by Zibo Hu, Kun Gao, Jingyi Wang, Zhijia Yang, Zefeng Zhang, Haobo Cheng, Wei Li

    Open-set object detection unifies candidate category object detection and remote sensing visual grounding, and can simultaneously meet candidate category multi-object detection and text-guided object detection. Most existing open-set detectors are developed based on candidate category detectors by introducing text information. These methods need to process text and images at the same time, which will increase their training overhead and computational complexity. The open-set detector consists of a backbone, neck, and prediction head, with the neck being the main source of computational complexity due to multi-scale self-attention and cross-modal attention. However, little research has focused on improving their computational efficiency while maintaining model performance. This paper addresses this gap by proposing an Enhanced Grounding DINO to optimize the neck network, reducing computational complexity while preserving model performance. Specifically, the key contributions are the proposed efficient cross-modality block, which consists of the Multi-Scale Visual-Cross-Text Fusion Module (MSVCTFM) and Inverse Pyramid Feature Refinement (IPFR). The efficient cross-modality block reduces the computational complexity of both multi-scale visual feature refinement and the fusion of text and visual features, while maintaining model performance. The MSVCTFM decouples and optimizes the fusion of multi-scale visual and text features, thereby enhancing model performance. The IPFR further reduces the computational complexity involved in refining multi-scale visual features. The method achieves a 49.7% reduction in GFLOPs, improves performance on visual grounding datasets DIOR-RSVG and RSVG-HR, and delivers competitive results on the candidate category dataset DOTA.