Author name cluster

Na 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.

7 papers

2 author rows

AAAI Conference 2026 Conference Paper

AquaSplatting: A Hybrid 3D Representation for Robust Underwater Scene Reconstruction via Dual-Branch Rendering

Jiangbei Hu
Haobo Wang
Baixin Xu
Nan Ding
Zhimao Lu
Na Lei
Ying He

While 3D Gaussian Splatting (3DGS) excels at real-time rendering of standard scenes, it struggles to reconstruct underwater environments due to severe challenges such as light scattering, color attenuation, and sparse coverage of Gaussian kernels in far-field aqueous regions. To address this, we introduce AquaSplatting, a hybrid framework that combines explicit and implicit modeling methods for robust underwater scene reconstruction. Our dual-branch architecture employs 3DGS in a geometry-guided branch to model solid surfaces like the seabed, while a medium-aware branch uses a compact, view-dependent MLP to represent volumetric water effects. Furthermore, a neural underwater hybrid rendering mechanism adaptively fuses these two representations based on accumulated opacity. Thanks to this dual-branch framework, our method can also synthesize restored images without water medium. To enhance efficiency, our proposed engagement-based pruning (EBP) strategy quantifies each Gaussian's contribution by accumulating its image-space gradients over multiple frames, enabling the principled removal of primitives with negligible impact. The entire framework is optimized using a comprehensive loss function that integrates photometric, exposure, semantic, and depth priors to maximize visual fidelity. Experiments on challenging underwater datasets demonstrate that AquaSplatting achieves the state-of-the-art in reconstruction quality surpassing prior methods while maintaining real-time performance.

PDF Details DOI

AAAI Conference 2026 Conference Paper

OT-ALD: Aligning Latent Distributions with Optimal Transport for Accelerated Image-to-Image Translation

Zhanpeng Wang
Shuting Cao
Yuhang Lu
YuhanLi
Na Lei
Zhongxuan Luo

The Dual Diffusion Implicit Bridge (DDIB) is an emerging image-to-image (I2I) translation method that preserves cycle consistency while achieving strong flexibility. It links two independently trained diffusion models (DMs) in the source and target domains by first adding noise to a source image to obtain a latent code, then denoising it in the target domain to generate the translated image. However, this method faces two key challenges: (1) low translation efficiency, and (2) translation trajectory deviations caused by mismatched latent distributions. To address these issues, we propose a novel I2I translation framework, OT-ALD, grounded in optimal transport (OT) theory, which retains the strengths of DDIB-based approach. Specifically, we compute an OT map from the latent distribution of the source domain to that of the target domain, and use the mapped distribution as the starting point for the reverse diffusion process in the target domain. Our error analysis confirms that OT-ALD eliminates latent distribution mismatches. Moreover, OT-ALD effectively balances faster image translation with improved image quality. Experiments on four translation tasks across three high-resolution datasets show that OT-ALD improves sampling efficiency by 20.29% and reduces the FID score by 2.6 on average compared to the top-performing baseline models.

PDF Details DOI

ICLR Conference 2023 Conference Paper

Volumetric Optimal Transportation by Fast Fourier Transform

Na Lei
Dongsheng An
Min Zhang 0069
Xiaoyin Xu
Xianfeng David Gu

The optimal transportation map finds the most economical way to transport one probability measure to another, and it has been applied in a broad range of applications in machine learning and computer vision. By the Brenier theory, computing the optimal transport map is equivalent to solving a Monge-Amp\`ere equation, which is highly non-linear. Therefore, the computation of optimal transportation maps is intrinsically challenging. In this work, we propose a novel and powerful method, the FFT-OT (fast Fourier transform-optimal transport), to compute the 3-dimensional OT problems. The method is based on several key ideas: first, the Monge-Amp\`ere equation is linearized to a sequence of linear elliptic PDEs with spacial and temporal variant coefficients; second, the obliqueness property of optimal transportation maps is reformulated as a Neumann boundary condition; and third, the variant coefficient elliptic PDEs are approximated by constant coefficient elliptic PDEs and solved by FFT on GPUs. We also prove that the algorithm converges linearly, namely the approximation error decreases exponentially fast. Experimental results show that the FFT-OT algorithm is more than a hundred times faster than the conventional methods based on the convex geometry. Furthermore, the method can be directly applied for sampling from complex 3D density functions in machine learning and magnifying the volumetric data in medical imaging.

Details

AAAI Conference 2022 Conference Paper

Efficient Optimal Transport Algorithm by Accelerated Gradient Descent

Dongsheng An
Na Lei
Xiaoyin Xu
Xianfeng Gu

Optimal transport (OT) plays an essential role in various areas like machine learning and deep learning. However, computing discrete OT for large scale problems with adequate accuracy and efficiency is highly challenging. Recently, methods based on the Sinkhorn algorithm add an entropy regularizer to the prime problem and obtain a trade off between efficiency and accuracy. In this paper, we propose a novel algorithm based on Nesterov’s smoothing technique to further improve the efficiency and accuracy in computing OT. Basically, the non-smooth c-transform of the Kantorovich potential is approximated by the smooth Log-Sum-Exp function, which smooths the original non-smooth Kantorovich dual functional. The smooth Kantorovich functional can be efficiently optimized by a fast proximal gradient method, the fast iterative shrinkage thresholding algorithm (FISTA). Theoretically, the computational complexity of the proposed method is lower than current estimation of the Sinkhorn algorithm in terms of the precision. Experimentally, compared with the Sinkhorn algorithm, our results demonstrate that the proposed method achieves faster convergence and better accuracy with the same parameter.

PDF Details

ICLR Conference 2020 Conference Paper

Ae-OT: a New Generative Model based on Extended Semi-discrete Optimal transport

Dongsheng An
Yang Guo
Na Lei
Zhongxuan Luo
Shing-Tung Yau
Xianfeng David Gu

Generative adversarial networks (GANs) have attracted huge attention due to its capability to generate visual realistic images. However, most of the existing models suffer from the mode collapse or mode mixture problems. In this work, we give a theoretic explanation of the both problems by Figalli’s regularity theory of optimal transportation maps. Basically, the generator compute the transportation maps between the white noise distributions and the data distributions, which are in general discontinuous. However, DNNs can only represent continuous maps. This intrinsic conflict induces mode collapse and mode mixture. In order to tackle the both problems, we explicitly separate the manifold embedding and the optimal transportation; the first part is carried out using an autoencoder to map the images onto the latent space; the second part is accomplished using a GPU-based convex optimization to find the discontinuous transportation maps. Composing the extended OT map and the decoder, we can finally generate new images from the white noise. This AE-OT model avoids representing discontinuous maps by DNNs, therefore effectively prevents mode collapse and mode mixture.

Details

ECAI Conference 2020 Conference Paper

MetaSelection: Metaheuristic Sub-Structure Selection for Neural Network Pruning Using Evolutionary Algorithm

Zixun Zhang
Zhen Li 0026
Lin Lin 0008
Na Lei
Guanbin Li
Shuguang Cui

Neural network pruning is widely applied to various mobile applications. Previous pruning methods mainly leverage ad-hoc criteria to evaluate channel importance. In this paper, we propose an effective metaheuristic sub-structure selection (MetaSelection) method for neural network pruning. MetaSelection exploits evolutionary algorithm (EA) to search the proper sub-structure satisfying the resource constraints. In comparison with previous AutoML based methods, MetaSelection can automatically achieve the pruning rate and channel selection at the same time instead of hand-crafted criteria in a cascaded way. Regarding the tremendous search space of channel selection as a combinatorial optimization problem, we further utilize a coarse-to-fine strategy and the novel probability distribution crossover (PDC) to speed up the search procedure. Besides, MetaSelection prunes the network globally rather than in a layer-by-layer way. We evaluate MetaSelection on several appealing deep neural networks, achieving superior results with adaptive depth and width. Concretely, on ImageNet, MetaSelection achieves a top-1 accuracy of 71. 5% on MobileNetV2 under 70% FLOPs constraint and a FLOPs reduction of 30% with 76. 4% top-1 accuracy for ResNet50.

Details

ICRA Conference 2017 Conference Paper

Robot Coverage Path planning for general surfaces using quadratic differentials

Yu-Yao Lin
Chien-Chun Ni
Na Lei
Xianfeng David Gu
Jie Gao 0001

Robot Coverage Path planning (i. e. , the process of providing full coverage of a given domain by one or multiple robots) is a classical problem in the field of robotics and motion planning. The goal of such planning is to provide nearly full coverage while also minimize duplicately visited area. In this paper, we focus on the scenario of path planning on general surface, including planar domains with complex topology, complex terrain, and general surface in 3D space. Our approach described in this paper adopts a natural, intrinsic and global parametrization of the surface for robot path planning, namely the holomorphic quadratic differentials. We give each point on the surface a uv-coordinates naturally represented by a complex number, except for a small number of zero points (singularities). We show that natural, efficient robot paths can be obtained by using such coordinate systems. The method is based on intrinsic geometry and thus can be adapted to general surface exploration in 3D.

Details