Author name cluster

Lei Lei

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

EAAI Journal 2026 Journal Article

A regional-information-fusion-based data augmentation method for hydrodynamic analysis of underwater gliders

Lijie Tan
Hongyu Wu
Lei Lei
Jinhu Cai
Zhiduo Tan
Shaoze Yan
Yunqiang Yang

Underwater gliders (UGs) known for low energy consumption, require excellent hydrodynamic shapes (HSs) to enhance their performance. However, the HS design heavily relies on time-consuming computational fluid dynamics (CFD) simulations, limiting the large-scale acquisition of datasets. Furthermore, existing research lacks in-depth exploration and expansion of the available datasets, resulting in poor data utilization. These limitations severely hinder advances in glider technology. Therefore, this paper proposes a regional feature information fusion method (RFIFM), which extracts and stores regional hydrodynamic characteristics from full-configuration CFD simulations, ensuring that regional information remains reusable within an integrated physical context. Then, a region information fusion data augmentation method (RIFDA) and corresponding hierarchical design of experiment method are proposed to expand the existing dataset to at least twice its original scale, achieving data reusability, while generating physics-consistent hydrodynamic data samples. Subsequently, the augmented dataset is trained using a machine learning method to achieve the high-efficiency prediction of hydrodynamic characteristics. This entire process forms a four-stage data-driven method integrating sampling, acquisition, augmentation and modeling of data. Finally, the proposed method is validated by solving the shape optimization problem for a morphing glider. This paper may provide certain theoretical guidance for the innovative design of UGs.

Details DOI

AAAI Conference 2026 Conference Paper

RAW-Flow: Advancing RGB-to-RAW Image Reconstruction with Deterministic Latent Flow Matching

Zhen Liu
Diedong Feng
Hai Jiang
Liaoyuan Zeng
Hao Wang
Chaoyu Feng
Lei Lei
Bing Zeng

RGB-to-RAW reconstruction, or the reverse modeling of a camera Image Signal Processing (ISP) pipeline, aims to recover high-fidelity RAW data from RGB images. Despite notable progress, existing learning-based methods typically treat this task as a direct regression objective and still struggle with detail inconsistency and color deviation, due to the ill-posed nature of inverse ISP and the inherent information loss in quantized RGB images. To address these limitations, we pioneer a generative perspective by reformulating RGB-to-RAW reconstruction as a deterministic latent transport problem and introduce a novel framework named RAW-Flow, which leverages flow matching to learn a deterministic vector field in latent space, to effectively bridge the gap between RGB and RAW representations and enable accurate reconstruction of structural details and color information. To further enhance latent transport, we introduce a cross-scale context guidance module that injects hierarchical RGB features into the flow estimation process. Moreover, we design a Dual-domain Latent Autoencoder (DLAE) with a feature alignment constraint to support the proposed latent transport framework, which jointly encodes RGB and RAW inputs while promoting stable training and high-fidelity reconstruction. Extensive experiments demonstrate that RAW-Flow outperforms state-of-the-art approaches both quantitatively and visually.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting

Nan Wang
Lixing Xiao
Yuantao Chen
Weiqing Xiao
Pierre Merriaux
Lei Lei
Ziyang Yan
Saining Zhang

Neural rendering techniques, including NeRF and Gaussian Splatting (GS), rely on photometric consistency to produce high-quality reconstructions. However, in real-world driving scenarios, it is challenging to guarantee perfect photometric consistency in acquired images. Appearance codes have been widely used to address this issue, but their modeling capability is limited, as a single code is applied to the entire image. Recently, the bilateral grid was introduced to perform pixel-wise color mapping, but it is difficult to optimize and constrain effectively. In this paper, we propose a novel multi-scale bilateral grid that unifies appearance codes and bilateral grids. We demonstrate that this approach significantly improves geometric accuracy in dynamic, decoupled autonomous driving scene reconstruction, outperforming both appearance codes and bilateral grids. This is crucial for autonomous driving, where accurate geometry is important for obstacle avoidance and control. Our method shows strong results across four datasets: Waymo, NuScenes, Argoverse, and PandaSet. We further demonstrate that the improvement in geometry is driven by the multi-scale bilateral grid, which effectively reduces floaters caused by photometric inconsistency.

PDF Details

AAAI Conference 2024 Conference Paper

Learning Real-World Image De-weathering with Imperfect Supervision

Xiaohui Liu
Zhilu Zhang
Xiaohe Wu
Chaoyu Feng
Xiaotao Wang
Lei Lei
Wangmeng Zuo

Real-world image de-weathering aims at removing various undesirable weather-related artifacts. Owing to the impossibility of capturing image pairs concurrently, existing real-world de-weathering datasets often exhibit inconsistent illumination, position, and textures between the ground-truth images and the input degraded images, resulting in imperfect supervision. Such non-ideal supervision negatively affects the training process of learning-based de-weathering methods. In this work, we attempt to address the problem with a unified solution for various inconsistencies. Specifically, inspired by information bottleneck theory, we first develop a Consistent Label Constructor (CLC) to generate a pseudo-label as consistent as possible with the input degraded image while removing most weather-related degradation. In particular, multiple adjacent frames of the current input are also fed into CLC to enhance the pseudo-label. Then we combine the original imperfect labels and pseudo-labels to jointly supervise the de-weathering model by the proposed Information Allocation Strategy (IAS). During testing, only the de-weathering model is used for inference. Experiments on two real-world de-weathering datasets show that our method helps existing de-weathering models achieve better performance. Code is available at https://github.com/1180300419/imperfect-deweathering.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes

Zhilu Zhang 0001
Haoyu Wang
Shuai Liu 0009
Xiaotao Wang
Lei Lei
Wangmeng Zuo

Merging multi-exposure images is a common approach for obtaining high dynamic range (HDR) images, with the primary challenge being the avoidance of ghosting artifacts in dynamic scenes. Recent methods have proposed using deep neural networks for deghosting. However, the methods typically rely on sufficient data with HDR ground-truths, which are difficult and costly to collect. In this work, to eliminate the need for labeled data, we propose SelfHDR, a self-supervised HDR reconstruction method that only requires dynamic multi-exposure images during training. Specifically, SelfHDR learns a reconstruction network under the supervision of two complementary components, which can be constructed from multi-exposure images and focus on HDR color as well as structure, respectively. The color component is estimated from aligned multi-exposure images, while the structure one is generated through a structure-focused network that is supervised by the color component and an input reference (\eg, medium-exposure) image. During testing, the learned reconstruction network is directly deployed to predict an HDR image. Experiments on real-world images demonstrate our SelfHDR achieves superior results against the state-of-the-art self-supervised methods, and comparable performance to supervised ones. Codes are available at https://github.com/cszhilu1998/SelfHDR

Details

AAAI Conference 2023 Conference Paper

SLOTH: Structured Learning and Task-Based Optimization for Time Series Forecasting on Hierarchies

Fan Zhou
Chen Pan
Lintao Ma
Yu Liu
Shiyu Wang
James Zhang
Xinxin Zhu
Xuanwei Hu

Multivariate time series forecasting with hierarchical structure is widely used in real-world applications, e.g., sales predictions for the geographical hierarchy formed by cities, states, and countries. The hierarchical time series (HTS) forecasting includes two sub-tasks, i.e., forecasting and reconciliation. In the previous works, hierarchical information is only integrated in the reconciliation step to maintain coherency, but not in forecasting step for accuracy improvement. In this paper, we propose two novel tree-based feature integration mechanisms, i.e., top-down convolution and bottom-up attention to leverage the information of the hierarchical structure to improve the forecasting performance. Moreover, unlike most previous reconciliation methods which either rely on strong assumptions or focus on coherent constraints only, we utilize deep neural optimization networks, which not only achieve coherency without any assumptions, but also allow more flexible and realistic constraints to achieve task-based targets, e.g., lower under-estimation penalty and meaningful decision-making loss to facilitate the subsequent downstream tasks. Experiments on real-world datasets demonstrate that our tree-based feature integration mechanism achieves superior performances on hierarchical forecasting tasks compared to the state-of-the-art methods, and our neural optimization networks can be applied to real-world tasks effectively without any additional effort under coherence and task-based constraints.

PDF Details DOI

EAAI Journal 2022 Journal Article

Differentially private frequent episode mining over event streams

Jiawen Qin
Jinyan Wang
Qiyu Li
Shijian Fang
Xianxian Li
Lei Lei

Frequent episode mining is a wide range framework of data mining from sequential data with many applications, which is a totally short-ordered collection of event-types and unearths temporal correlations without information loss over event streams. While offering substantial benefits, directly releasing frequent episodes to the public will enormously threaten the individual’s privacy. However, there is little work so far concentrating on privately frequent episode mining. In this paper, we investigate the privacy problem in mining frequent episodes from event streams due to continuous releases in successive windows and propose a real-time differentially private frequent episode mining algorithm over event streams to avoid the privacy leakage with ω -event privacy guarantee. To obtain private frequent episodes, we propose a sample-based perturbation approach, which improves the accuracy of selecting frequent episodes based on sampling databases. To reduce the privately mining time and avoid repeatedly privacy budget allocation to coincident window of adjacent releases as much as possible, we present an incremental perturbation approach according to the judgment in dissimilarity calculation mechanism. Meanwhile, in order to protect data collected from any ω successive timestamps over event streams, we employ an adaptive ω -event privacy mechanism on the basis of the dynamicity of episodes. Finally, experimental results on real-world datasets demonstrate the effectiveness and efficiency of our algorithm.

Details DOI

IJCAI Conference 2022 Conference Paper

Memory Augmented State Space Model for Time Series Forecasting

Yinbo Sun
Lintao Ma
Yu Liu
Shijun Wang
James Zhang
Yangfei Zheng
Hu Yun
Lei Lei

State space model (SSM) provides a general and flexible forecasting framework for time series. Conventional SSM with fixed-order Markovian assumption often falls short in handling the long-range temporal dependencies and/or highly non-linear correlation in time-series data, which is crucial for accurate forecasting. To this extend, we present External Memory Augmented State Space Model (EMSSM) within the sequential Monte Carlo (SMC) framework. Unlike the common fixed-order Markovian SSM, our model features an external memory system, in which we store informative latent state experience, whereby to create ``memoryful" latent dynamics modeling complex long-term dependencies. Moreover, conditional normalizing flows are incorporated in our emission model, enabling the adaptation to a broad class of underlying data distributions. We further propose a Monte Carlo Objective that employs an efficient variational proposal distribution, which fuses the filtering and the dynamic prior information, to approximate the posterior state with proper particles. Our results demonstrate the competitiveness of forecasting performance of our proposed model comparing with other state-of-the-art SSMs.

PDF Details DOI