Xingyi Du
Research Subjects
Xingyi Du has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Nathan Carr
Adobe Research, San Jose, USA
4 shared publications - Qingnan Zhou
Adobe Research, New York, USA
4 shared publications - Tao Ju
Washington University in St. Louis, SAINT LOUIS, USA
4 shared publications - Yiwen Ju
Washington University in St. Louis, SAINT LOUIS, USA
4 shared publications - Zherong Pan
LightSpeed Studios
2 shared publications - Cao Hongyi
Hangzhou Dianzi University, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-14
CSG Sweeps: Feature-aware sweep surfacing of deformable CSGs
Computing the sweep surface of a moving 3D solid is a fundamental problem in computer graphics. The problem is particularly challenging when the solid is piecewise-smooth, which yields a complex network of sharp features on the sweep surface. Few methods can model these features, and they are all limited to rigid-body motions (translation and rotation). We present the first feature-aware method to surface the sweep of a deforming piecewise-smooth shape. Our method works on any input represented as a 4D time-varying CSG, allowing changes to both geometry and topology during sweeping. Our technical contributions include a generalization of the lifted sweeping formulation from smooth functions to CSG functions, and robust algorithms for discretizing multiple intersecting implicit surfaces in arbitrary dimensions. We demonstrate our algorithm for capturing the sharp features on the sweep surface under both rigid and non-rigid motions.
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-14
Open AccessCSG Sweeps: Feature-aware sweep surfacing of deformable CSGs
Computing the sweep surface of a moving 3D solid is a fundamental problem in computer graphics. The problem is particularly challenging when the solid is piecewise-smooth, which yields a complex network of sharp features on the sweep surface. Few methods can model these features, and they are all limited to rigid-body motions (translation and rotation). We present the first feature-aware method to surface the sweep of a deforming piecewise-smooth shape. Our method works on any input represented as a 4D time-varying CSG, allowing changes to both geometry and topology during sweeping. Our technical contributions include a generalization of the lifted sweeping formulation from smooth functions to CSG functions, and robust algorithms for discretizing multiple intersecting implicit surfaces in arbitrary dimensions. We demonstrate our algorithm for capturing the sharp features on the sweep surface under both rigid and non-rigid motions.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 4915-4930
Practical Occluder Generation for Mobile Games
Occlusion culling is a cornerstone of real-time rendering, particularly in mobile games where limited GPU bandwidth demands highly efficient scene management. At the heart of occlusion culling lies the use of simplified proxy geometry-called occluders-that approximate scene geometry for rapid visibility testing. However, producing high-quality occluders that are low in polygon count, conservative in coverage, and tightly aligned with the original geometry remains a manual and labor-intensive process. In this paper, we present a fast and fully automated two-stage approach for robust occluder generation tailored to real-world game assets. Our method begins with a novel strategy for inward offset mesh computation, followed by a conservative simplification step leveraging a new variant of Quadric Error Metrics (QEM). This approach effectively handles noisy and topologically complex inputs, generating production-ready occluders in seconds. Extensive experiments on a wide range of asset types demonstrate that our technique achieves aggressive triangle reduction while preserving critical occlusion fidelity. By offering a practical and scalable solution, our method bridges the gap between academic research and demanding needs for game development.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 4915-4930
Practical Occluder Generation for Mobile Games
Occlusion culling is a cornerstone of real-time rendering, particularly in mobile games where limited GPU bandwidth demands highly efficient scene management. At the heart of occlusion culling lies the use of simplified proxy geometry-called occluders-that approximate scene geometry for rapid visibility testing. However, producing high-quality occluders that are low in polygon count, conservative in coverage, and tightly aligned with the original geometry remains a manual and labor-intensive process. In this paper, we present a fast and fully automated two-stage approach for robust occluder generation tailored to real-world game assets. Our method begins with a novel strategy for inward offset mesh computation, followed by a conservative simplification step leveraging a new variant of Quadric Error Metrics (QEM). This approach effectively handles noisy and topologically complex inputs, generating production-ready occluders in seconds. Extensive experiments on a wide range of asset types demonstrate that our technique achieves aggressive triangle reduction while preserving critical occlusion fidelity. By offering a practical and scalable solution, our method bridges the gap between academic research and demanding needs for game development.
- Open Access
- 14 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (2) , 1
Erratum: Lifted Surfacing of Generalized Sweep Volumes
This is an erratum for the article “Lifted Surfacing of Generalized Sweep Volumes” published in ACM Trans. Graph. 44, 6, Article 249 (December 2025), 17 pages.
- 14 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (2) , 1
Open AccessErratum: Lifted Surfacing of Generalized Sweep Volumes
This is an erratum for the article “Lifted Surfacing of Generalized Sweep Volumes” published in ACM Trans. Graph. 44, 6, Article 249 (December 2025), 17 pages.
- Open Access
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-12
RL-ACD: Reinforcement Learning-based Approximate Convex Decomposition
Approximate Convex Decomposition (ACD) aims to approximate complex 3D shapes with convex components, which is widely applied to create compact collision representations for real-time applications, including VR/AR, interactive games, and robotic simulations. Efficiency and optimality are critical for ACD algorithms in approximating large-scale, complex 3D shapes, enabling high-quality decompositions with minimal components. Unfortunately, existing methods either employ sub-optimal greedy strategies or rely on computationally intensive multi-step searches. In this work, we propose RL-ACD, a data-driven, reinforcement learning-based approach for efficient and near-optimal convex shape decomposition. We formulate ACD as a Markov Decision Process (MDP), where cutting planes are iteratively applied based on the current stage's mesh fragments rather than the entire fine-grained mesh, leading to a novel, efficient geometric encoding. To train near-optimal policies for ACD, we propose a novel dual-state Bellman loss and analyze its convergence using a Q-learning algorithm. Comprehensive evaluations across diverse datasets validate the efficiency and accuracy of RL-ACD for convex decomposition tasks. Our method outperforms the multi-step tree search by 15× in terms of computational speed, while reducing the number of resulting components by 16% compared to the current state-of-the-art greedy algorithms, significantly narrowing the sub-optimality gap and enhancing downstream task performance.
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-12
Open AccessRL-ACD: Reinforcement Learning-based Approximate Convex Decomposition
Approximate Convex Decomposition (ACD) aims to approximate complex 3D shapes with convex components, which is widely applied to create compact collision representations for real-time applications, including VR/AR, interactive games, and robotic simulations. Efficiency and optimality are critical for ACD algorithms in approximating large-scale, complex 3D shapes, enabling high-quality decompositions with minimal components. Unfortunately, existing methods either employ sub-optimal greedy strategies or rely on computationally intensive multi-step searches. In this work, we propose RL-ACD, a data-driven, reinforcement learning-based approach for efficient and near-optimal convex shape decomposition. We formulate ACD as a Markov Decision Process (MDP), where cutting planes are iteratively applied based on the current stage's mesh fragments rather than the entire fine-grained mesh, leading to a novel, efficient geometric encoding. To train near-optimal policies for ACD, we propose a novel dual-state Bellman loss and analyze its convergence using a Q-learning algorithm. Comprehensive evaluations across diverse datasets validate the efficiency and accuracy of RL-ACD for convex decomposition tasks. Our method outperforms the multi-step tree search by 15× in terms of computational speed, while reducing the number of resulting components by 16% compared to the current state-of-the-art greedy algorithms, significantly narrowing the sub-optimality gap and enhancing downstream task performance.
- Open Access
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-17
Lifted Surfacing of Generalized Sweep Volumes
Computing the boundary surface of the 3D volume swept by a rigid or deforming solid remains a challenging problem in geometric modeling. Existing approaches are often limited to sweeping rigid shapes, cannot guarantee a watertight surface, or struggle with modeling the intricate geometric features (e.g., sharp creases and narrow gaps) and topological features (e.g., interior voids). We make the observation that the sweep boundary is a subset of the projection of the intersection of two implicit surfaces in a higher dimension, and we derive a characterization of the subset using winding numbers. These insights lead to a general algorithm for any sweep represented as a smooth time-varying implicit function satisfying a genericity assumption, and it produces a watertight and intersection-free surface that better approximates the geometric and topological features than existing methods.
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-17
Open AccessLifted Surfacing of Generalized Sweep Volumes
Computing the boundary surface of the 3D volume swept by a rigid or deforming solid remains a challenging problem in geometric modeling. Existing approaches are often limited to sweeping rigid shapes, cannot guarantee a watertight surface, or struggle with modeling the intricate geometric features (e.g., sharp creases and narrow gaps) and topological features (e.g., interior voids). We make the observation that the sweep boundary is a subset of the projection of the intersection of two implicit surfaces in a higher dimension, and we derive a characterization of the subset using winding numbers. These insights lead to a general algorithm for any sweep represented as a smooth time-varying implicit function satisfying a genericity assumption, and it produces a watertight and intersection-free surface that better approximates the geometric and topological features than existing methods.
- Open Access
- 29 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 22-28
Random Affine Transformation Feature Representation Learning for Fast Polygon Retrieval
Despite the advance of representation learning (RL) of image and text data, it is a challenging task to obtain a general-purpose representation of vector-based spatial data (e.g., point, polyline, and polygon) that fulfills domain-specific prerequisites in downstream spatial analysis. Towards filling this gap, we put focus on the first step of revisiting a classic computational geometry task, namely the polygon retrieval, with a modern RL approach. In this paper, we propose a novel representation learning method for polygon data, namely Random Affine Transformation Features (RATFs). Inspired by Random Fourier Features, RATFs represent polygons on the plane into vector embeddings in the high-dimensional space using the basis of random anchor polygons, allowing us to transform complex, non-batch-wise computations between polygons such as Hausdorff distance into simple, batch-wise inner products. Experiments demonstrate that by using a naive 3-layer feed-forward network, our RATFs-based neural polygon embeddings are able to retrieve similar polygons from the corpus 100,000 times faster than computing Hausdorff distances at inferencing and achieve good retrieval quality. We aim to demonstrate the representational power of RATFs and leave the design and tuning of more advanced RATFs-based neural networks for future work.
- 29 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 22-28
Open AccessRandom Affine Transformation Feature Representation Learning for Fast Polygon Retrieval
Despite the advance of representation learning (RL) of image and text data, it is a challenging task to obtain a general-purpose representation of vector-based spatial data (e.g., point, polyline, and polygon) that fulfills domain-specific prerequisites in downstream spatial analysis. Towards filling this gap, we put focus on the first step of revisiting a classic computational geometry task, namely the polygon retrieval, with a modern RL approach. In this paper, we propose a novel representation learning method for polygon data, namely Random Affine Transformation Features (RATFs). Inspired by Random Fourier Features, RATFs represent polygons on the plane into vector embeddings in the high-dimensional space using the basis of random anchor polygons, allowing us to transform complex, non-batch-wise computations between polygons such as Hausdorff distance into simple, batch-wise inner products. Experiments demonstrate that by using a naive 3-layer feed-forward network, our RATFs-based neural polygon embeddings are able to retrieve similar polygons from the corpus 100,000 times faster than computing Hausdorff distances at inferencing and achieve good retrieval quality. We aim to demonstrate the representational power of RATFs and leave the design and tuning of more advanced RATFs-based neural networks for future work.
- Open Access
- 19 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (4) , 1-17
Adaptive grid generation for discretizing implicit complexes
We present a method for generating a simplicial (e.g., triangular or tetrahedral) grid to enable adaptive discretization of implicit shapes defined by a vector function. Such shapes, which we call implicit complexes, are generalizations of implicit surfaces and useful for representing non-smooth and non-manifold structures. While adaptive grid generation has been extensively studied for polygonizing implicit surfaces, few methods are designed for implicit complexes. Our method can generate adaptive grids for several implicit complexes, including arrangements of implicit surfaces, CSG shapes, material interfaces, and curve networks. Importantly, our method adapts the grid to the geometry of not only the implicit surfaces but also their lower-dimensional intersections. We demonstrate how our method enables efficient and detail-preserving discretization of non-trivial implicit shapes.
- 19 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (4) , 1-17
Open AccessAdaptive grid generation for discretizing implicit complexes
We present a method for generating a simplicial (e.g., triangular or tetrahedral) grid to enable adaptive discretization of implicit shapes defined by a vector function. Such shapes, which we call implicit complexes, are generalizations of implicit surfaces and useful for representing non-smooth and non-manifold structures. While adaptive grid generation has been extensively studied for polygonizing implicit surfaces, few methods are designed for implicit complexes. Our method can generate adaptive grids for several implicit complexes, including arrangements of implicit surfaces, CSG shapes, material interfaces, and curve networks. Importantly, our method adapts the grid to the geometry of not only the implicit surfaces but also their lower-dimensional intersections. We demonstrate how our method enables efficient and detail-preserving discretization of non-trivial implicit shapes.
- Open Access
- 29 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Isometric Energies for Recovering Injectivity in Constrained Mapping
Computing injective maps with low distortions is a long-standing problem in computer graphics. Such maps are particularly challenging to obtain in the presence of positional constraints, because an injective initial map is often not available. Recently, several energies were proposed and shown to be highly successful in optimizing injectivity from non-injective initial maps while satisfying positional constraints. However, minimizing these energies tends to produce elements with significant isometric distortions. This paper presents simple variants of these energies that retain their desirable traits while promoting isometry. While our method is not guaranteed to provide an injective map, we observe that, on large-scale 2D and 3D data sets, minimizing the proposed isometric variants results in a similar level of success in recovering injectivity as the original energies but a significantly lower isometric distortion.
- 29 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessIsometric Energies for Recovering Injectivity in Constrained Mapping
Computing injective maps with low distortions is a long-standing problem in computer graphics. Such maps are particularly challenging to obtain in the presence of positional constraints, because an injective initial map is often not available. Recently, several energies were proposed and shown to be highly successful in optimizing injectivity from non-injective initial maps while satisfying positional constraints. However, minimizing these energies tends to produce elements with significant isometric distortions. This paper presents simple variants of these energies that retain their desirable traits while promoting isometry. While our method is not guaranteed to provide an injective map, we observe that, on large-scale 2D and 3D data sets, minimizing the proposed isometric variants results in a similar level of success in recovering injectivity as the original energies but a significantly lower isometric distortion.