Author name cluster

Wencheng Wang

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.

9 papers

1 author row

EAAI Journal 2026 Journal Article

A hybrid deep learning model integrating interpretability and cloud model for dam deformation and dynamic risk early warning

Wencheng Wang
Xiuwen Li
Hao Wu
Qiang Yue

Accurate and interpretable deformation prediction remains a critical challenge in the field of intelligent dam health monitoring. To address the limitations of existing deep learning models in generalization capability and decision transparency, this study proposes a novel hybrid deep learning framework. This framework achieves a deep integration of the Transformer architecture, which captures global dependencies, and the Bidirectional Long Short-Term Memory network, which models local temporal dynamics, thereby significantly enhancing predictive accuracy and generalization. Furthermore, we incorporate Shapley additive explanations and a cloud model to establish an integrated "prediction-attribution-assessment" pipeline. In a case study of a hydraulic hub on the Yellow River's main stream in Ningxia, China, all six developed deformation prediction models demonstrated excellent performance, with a Mean Squared Error below 0. 029 and a Mean Absolute Error below 0. 137, significantly outperforming three other widely-used deep learning models in dam deformation prediction. Shapley additive explanations identified five critical risk-influencing factors, including previous time-step deformation and dam foundation joint opening displacement. The cloud model further enabled the quantitative assessment of dynamic risk evolution. This work facilitates a paradigm shift in dam safety monitoring from "black-box forecasting" towards "transparent decision-making, " offering a solution with both theoretical and practical merits for real-time risk management.

Details DOI

AAAI Conference 2025 Conference Paper

Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction

Cheng Xu
Fei Hou
Wencheng Wang
Hong Qin
Zhebin Zhang
Ying He

While Signed Distance Fields (SDF) are well-established for modeling watertight surfaces, Unsigned Distance Fields (UDF) broaden the scope to include open surfaces and models with complex inner structures. Despite their flexibility, UDFs encounter significant challenges in high-fidelity 3D reconstruction, such as non-differentiability at the zero level set, difficulty in achieving the exact zero value, numerous local minima, vanishing gradients, and oscillating gradient directions near the zero level set. To address these challenges, we propose Details Enhanced UDF (DEUDF) learning that integrates normal alignment and the SIREN network for capturing fine geometric details, adaptively weighted Eikonal constraints to address vanishing gradients near the target surface, unconditioned MLP-based UDF representation to relax non-negativity constraints, and DCUDF for extracting the local minimal average distance surface. These strategies collectively stabilize the learning process from unoriented point clouds and enhance the accuracy of UDFs. Our computational results demonstrate that DEUDF outperforms existing UDF learning methods in both accuracy and the quality of reconstructed surfaces.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstruction

Xuhui Chen
Fei Hou
Wencheng Wang
Hong Qin
Ying He

Unsigned distance fields (UDFs) are widely used in 3D deep learning due to their ability to represent shapes with arbitrary topology. While prior work has largely focused on learning UDFs from point clouds or multi-view images, extracting meshes from UDFs remains challenging, as the learned fields rarely attain exact zero distances. A common workaround is to reconstruct signed distance fields (SDFs) locally from UDFs to enable surface extraction via Marching Cubes. However, this often introduces topological artifacts such as holes or spurious components. Moreover, local SDFs are inherently incapable of representing non-manifold geometry, leading to complete failure in such cases. To address this gap, we propose MIND ($\mathrm{\underline{M}aterial}$ $\mathrm{\underline{I}nterface}$ $\mathrm{from}$ $\mathrm{\underline{N}on}$-$\mathrm{manifold}$ $\mathrm{\underline{D}istance}$ $\mathrm{fields}$), a novel algorithm for generating material interfaces directly from UDFs, enabling non-manifold mesh extraction from a global perspective. The core of our method lies in deriving a meaningful spatial partitioning from the UDF, where the target surface emerges as the interface between distinct regions. We begin by computing a two-signed local field to distinguish the two sides of manifold patches, and then extend this to a multi-labeled global field capable of separating all sides of a non-manifold structure. By combining this multi-labeled field with the input UDF, we construct material interfaces that support non-manifold mesh extraction via a multi-labeled Marching Cubes algorithm. Extensive experiments on UDFs generated from diverse data sources, including point cloud reconstruction, multi-view reconstruction, and medial axis transforms, demonstrate that our approach robustly handles complex non-manifold surfaces and significantly outperforms existing methods. The source code is available at https: //github. com/jjjkkyz/MIND.

PDF Details

NeurIPS Conference 2024 Conference Paper

From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $\alpha$-NeuS

Haoran Zhang
Junkai Deng
Xuhui Chen
Fei Hou
Wencheng Wang
Hong Qin
Chen Qian
Ying He

Traditional 3D shape reconstruction techniques from multi-view images, such as structure from motion and multi-view stereo, face challenges in reconstructing transparent objects. Recent advances in neural radiance fields and its variants primarily address opaque or transparent objects, encountering difficulties to reconstruct both transparent and opaque objects simultaneously. This paper introduces $\alpha$-NeuS$\textemdash$an extension of NeuS$\textemdash$that proves NeuS is unbiased for materials from fully transparent to fully opaque. We find that transparent and opaque surfaces align with the non-negative local minima and the zero iso-surface, respectively, in the learned distance field of NeuS. Traditional iso-surfacing extraction algorithms, such as marching cubes, which rely on fixed iso-values, are ill-suited for such data. We develop a method to extract the transparent and opaque surface simultaneously based on DCUDF. To validate our approach, we construct a benchmark that includes both real-world and synthetic scenes, demonstrating its practical utility and effectiveness. Our data and code are publicly available at https: //github. com/728388808/alpha-NeuS.

PDF Details DOI

TCS Journal 2023 Journal Article

Delay-constrained minimum shortest path trees and related problems

Junran Lichen
Lijian Cai
Jianping Li
Suding Liu
Pengxiang Pan
Wencheng Wang

Motivated by some applications in communication networks of the diameter-constrained minimum spanning tree (Diamc-MST) problem, we address the delay-constrained minimum shortest path tree (Delayc-MSPT) problem, which is a variation of the Diamc-MST problem. Specifically, given a weighted graph G = ( V, E; w, c ) and a constant d 0, where n = | V |, m = | E |, length function w: E → R + and cost function c: E → R +, we are asked to determine a minimum shortest path tree among all shortest path trees (in G) whose delays are no more than d 0, where the delay of a shortest path tree is the maximum distance (with respect to w ( ⋅ ) ) from its source to every other leaf in that tree, and the cost of such a shortest path tree is the sum of costs of all edges (with respect to c ( ⋅ ) ) in that tree. In addition, when a constant d 0 is the radius of G, we refer to this version of the Delayc-MSPT problem as the minimum radius minimum shortest path tree (MinRadius-MSPT) problem, and when a constant d 0 is the diameter of G, we refer to that version of the Delayc-MSPT problem as the maximum delay minimum shortest path tree (MaxDelay-MSPT) problem. In addition, we consider the diameter-constrained minimum shortest path tree (Diamc-MSPT) problem, except substituting the diameter for the delay of G in the Delayc-MSPT problem, where the diameter of a shortest path tree is the maximum distance (with respect to w ( ⋅ ) ) between any two leaves in that tree. The main contribution of our paper is to show the following results. (1) We design an exact algorithm to solve the Delayc-MSPT problem and a similar exact algorithm to solve the MinRadius-MSPT problem, respectively, and these two algorithms run in time O ( n 3 ); (2) We present an exact algorithm to solve the MaxDelay-MSPT problem, and that algorithm runs in time O ( n 3 ); (3) We provide an exact algorithm to solve the special version of the Diamc-MSPT problem, where the constant d 0 is exactly the diameter of G, and that algorithm runs in time O ( m n 2 + n 3 log ⁡ n ).

Details DOI

IJCAI Conference 2023 Conference Paper

Image Composition with Depth Registration

Zan Li
Wencheng Wang
Fei Hou

Handling occlusions is still a challenging problem for image composition. It always requires the source contents to be completely in front of the target contents or needs manual interventions to adjust occlusions, which is very tedious. Though several methods have suggested exploiting priors or learning techniques for promoting occlusion determination, their potentials are much limited. This paper addresses the challenge by presenting a depth registration method for merging the source contents seamlessly into the 3D space that the target image represents. Thus, the occlusions between the source contents and target contents can be conveniently handled through pixel-wise depth comparisons, allowing the user to more efficiently focus on the designs for image composition. Experimental results show that we can conveniently handle occlusions in image composition and improve efficiency by about 4 times compared to Photoshop.

PDF Details DOI

TCS Journal 2019 Journal Article

On some matching problems under the color-spanning model

Sergey Bereg
Feifei Ma
Wencheng Wang
Jian Zhang
Binhai Zhu

Given a set of n points Q in the plane, each colored with one of the k given colors, a color-spanning set S ⊂ Q is a subset of k points with distinct colors. The minimum diameter color-spanning set (MDCS) is a color-spanning set whose diameter is minimum. Somehow symmetrically, the largest closest pair color-spanning set (LCPCS) is a color-spanning set whose closest pair is the largest. Both MDCS and LCPCS have been shown to be NP-complete, but whether they are fixed-parameter tractable (FPT) when k is a parameter is open. Motivated by this question, we consider the FPT tractability of some matching problems under this color-spanning model, where 2k is the parameter. We show that the following three problems are polynomially solvable (hence FPT): (1) MinSum Matching Color-Spanning Set, (2) MaxMin Matching Color-Spanning Set, and (3) MinMax Matching Color-Spanning Set. For the k-Multicolored Independent Matching problem, namely, computing a matching of 2k vertices in a graph such that the vertices of the edges in the matching do not share edges, we show that it is W[1]-hard. Finally, motivated by this problem, which is related to the parameterized independent set problem, we are able to prove that LCPCS is W[1]-hard.

Details DOI

TCS Journal 2018 Journal Article

Finding disjoint dense clubs in a social network

Peng Zou
Hui Li
Wencheng Wang
Chunlin Xin
Binhai Zhu

In a social network, the trust among its members usually cannot be carried over many hops. So it is important to find disjoint clusters with a small diameter and with a decent size, formally called dense clubs. We focus on handling this NP-complete problem in this paper. First, from the parameterized computational complexity point of view, we show that this problem does not admit a polynomial kernel (implying that it is unlikely to apply some reduction rules to obtain a practically small problem size). Then, we focus on the dual version of the problem, i. e. , deleting d vertices to obtain some isolated dense clubs. We show that this dual problem admits a simple FPT algorithm using a bounded search tree method (the running time is still too high for practical datasets). Finally, we combine a simple reduction rule together with two branching rules to obtain a practical solution (verified by extensive testing on practical datasets).

Details DOI

TCS Journal 2014 Journal Article

Voronoi diagram with visual restriction

Chenglin Fan
Jun Luo
Wencheng Wang
Binhai Zhu

In a normal Voronoi diagram, each site is able to see all the points in the plane. In this paper, we study the case such that each site is only able to see a visually restricted region in the plane and construct the so-called Visual Restriction Voronoi Diagram (VRVD). We show that the visual restriction Voronoi cell of each site is not necessarily convex and it could consist of many disjoint regions. We prove that the combinatorial complexity of the VRVD on n sites is Θ ( n 2 ), and then show that the VRVD can be constructed in O ( n 2 ) time and O ( n 2 ) space. Besides that, we also give another algorithm with an extra log n factor of running time to compute VRVD, which is easy to implement in practice.

Details DOI