Yanwen Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yanwen Guo has a total of 306 co-authors. Here are the top co-authors by number of shared publications:
- Jie Guo
Nanjing University, Nanjing, China
58 shared publications - Yuanqi Li
Nanjing University
14 shared publications - Mingqiang Wei
Nanjing University of Aeronautics and Astronautics, Nanjing, China
8 shared publications - Ling-Qi Yan
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
7 shared publications - Jingwu He
National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
6 shared publications - Letian Huang
State Key Lab for Novel Software Technology, Nanjing University, Nanjing, China
6 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1
Corrigendum: Efficient Fur and Hair Multiple Scattering Using Volumetric Approximation
This is a corrigendum for the article "Efficient Fur and Hair Multiple Scattering Using Volumetric Approximation" published in ACM Trans. Graph. 45, 4, Article 92 (July 2026), 12 pages.
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1
Open AccessCorrigendum: Efficient Fur and Hair Multiple Scattering Using Volumetric Approximation
This is a corrigendum for the article "Efficient Fur and Hair Multiple Scattering Using Volumetric Approximation" published in ACM Trans. Graph. 45, 4, Article 92 (July 2026), 12 pages.
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 16990-17002
AMPTrack: Tracking Objects Using Appearance and Motion Prompts
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 16990-17002
AMPTrack: Tracking Objects Using Appearance and Motion Prompts
- 12 September 2026
- Published by Springer Nature
- p. 639-657
DOGE: Differentiable Bézier Graph Optimization for Road Network Extraction
- 12 September 2026
- Published by Springer Nature
- p. 639-657
DOGE: Differentiable Bézier Graph Optimization for Road Network Extraction
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Flatten the Complex: Joint B-Rep Generation via Compositional k-Cell Particles
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessFlatten the Complex: Joint B-Rep Generation via Compositional k-Cell Particles
- Open Access
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-15
Bounding Stratified Bernoulli Impulses for Ray Marching Gaussian Process Implicit Surfaces
The theory of light transport on Gaussian process implicit surface (GPIS) provides a unified framework for rendering surfaces, participating media, and the intermediate spectrum. However, previous approaches rely on brute-force ray marching for surface intersections, requiring full noise evaluations at each marching point, whether using multivariate Gaussian sampling or sparse convolution noise approximation. This imposes a severe limitation on the rendering efficiency. In this paper, we derive bounds to significantly reduce the total number of full noise evaluations, leading to efficient ray marching for ray-surface intersections. We introduce stratified Bernoulli impulses, enabling a fast point-level bound for individual realizations to replace unnecessary full noise evaluations. To further reduce the number of point-level bound evaluations, we propose a region-level bound, leveraging a spatial acceleration structure to prune probabilistically empty regions, thereby avoiding unnecessary marching points in advance. By combining these two bounds, our bounded ray marching accelerates ray-surface intersections in GPIS, and consequently significantly improves overall GPIS rendering efficiency. Code for this paper are at https://github.com/Cchen-77/bounded-gpis.
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-15
Open AccessBounding Stratified Bernoulli Impulses for Ray Marching Gaussian Process Implicit Surfaces
The theory of light transport on Gaussian process implicit surface (GPIS) provides a unified framework for rendering surfaces, participating media, and the intermediate spectrum. However, previous approaches rely on brute-force ray marching for surface intersections, requiring full noise evaluations at each marching point, whether using multivariate Gaussian sampling or sparse convolution noise approximation. This imposes a severe limitation on the rendering efficiency. In this paper, we derive bounds to significantly reduce the total number of full noise evaluations, leading to efficient ray marching for ray-surface intersections. We introduce stratified Bernoulli impulses, enabling a fast point-level bound for individual realizations to replace unnecessary full noise evaluations. To further reduce the number of point-level bound evaluations, we propose a region-level bound, leveraging a spatial acceleration structure to prune probabilistically empty regions, thereby avoiding unnecessary marching points in advance. By combining these two bounds, our bounded ray marching accelerates ray-surface intersections in GPIS, and consequently significantly improves overall GPIS rendering efficiency. Code for this paper are at https://github.com/Cchen-77/bounded-gpis.
- Open Access
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-12
Efficient Fur and Hair Multiple Scattering Using Volumetric Approximation
In this paper, we propose an efficient method for hair and fur rendering that approximates multiple scattering as volumetric light transport, achieving near path-traced visual fidelity at a drastically reduced cost. Multiple scattering among hair fibers is crucial for a realistic appearance, especially for light-colored hair, but it is extremely expensive to simulate directly. Prior approximations, such as dual scattering and fur BSSRDF, improve performance but often fail for dense hair/fur, yielding an overly dry or blurred appearance. Unlike previous volumetric hair rendering solutions, we treat dense hair/fur as a highly anisotropic participating medium to capture soft volumetric illumination, while still using explicit fiber geometry for direct lighting to preserve fine details. We accumulate hair fiber coverage in screen space and stochastically sample a single-scattering event to approximate higher-order scattering. Our method reproduces the rich appearance of hair and fur resulting from multiple scattering, while running about 7–10× faster than path tracing, making it suitable for use in production. We also demonstrate that our approach is robust under a variety of lighting conditions.
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-12
Open AccessEfficient Fur and Hair Multiple Scattering Using Volumetric Approximation
In this paper, we propose an efficient method for hair and fur rendering that approximates multiple scattering as volumetric light transport, achieving near path-traced visual fidelity at a drastically reduced cost. Multiple scattering among hair fibers is crucial for a realistic appearance, especially for light-colored hair, but it is extremely expensive to simulate directly. Prior approximations, such as dual scattering and fur BSSRDF, improve performance but often fail for dense hair/fur, yielding an overly dry or blurred appearance. Unlike previous volumetric hair rendering solutions, we treat dense hair/fur as a highly anisotropic participating medium to capture soft volumetric illumination, while still using explicit fiber geometry for direct lighting to preserve fine details. We accumulate hair fiber coverage in screen space and stochastically sample a single-scattering event to approximate higher-order scattering. Our method reproduces the rich appearance of hair and fur resulting from multiple scattering, while running about 7–10× faster than path tracing, making it suitable for use in production. We also demonstrate that our approach is robust under a variety of lighting conditions.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 6379-6390
Surface Reconstruction From Point Clouds via Image-Free Point-to-Gaussian Inference
The task of surface reconstruction from point clouds is to produce high-quality meshes using sampled 3D points (no images available). Traditional methods primarily focus on geometric accuracy but often produce meshes without texture colors. In this paper, we present a brand-new perspective in point cloud reconstruction task-Imagining points as more informative Gaussian splats and obtaining colored surfaces through free-form Gaussian-rendering reconstruction. We train a universal Point-to-Gaussian model to infer the attributes of Gaussian splats for any given pointcloud with merely point coordinates (and color optionally) as input, without requiring any image. Significant technical designs are applied on initialization, regularization and loss functions, making the whole learning process stable. The inferred Gaussian splats can faithfully recover the original appearance of objects or scenes (capable of quick rendering from any viewpoint, like human's imagination ability), meanwhile closely adhering to the input shape. After obtaining a sufficient number of virtually rendered images and depth maps, we employ the truncated signed distance function (TSDF) fusion to get the reconstruction results, producing high-quality and colored meshes. Extensive experiments demonstrate that our approach surpasses state-of-the-art methods in surface reconstruction metrics while maintaining high efficiency and simplicity.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (7) , 6379-6390
Surface Reconstruction From Point Clouds via Image-Free Point-to-Gaussian Inference
The task of surface reconstruction from point clouds is to produce high-quality meshes using sampled 3D points (no images available). Traditional methods primarily focus on geometric accuracy but often produce meshes without texture colors. In this paper, we present a brand-new perspective in point cloud reconstruction task-Imagining points as more informative Gaussian splats and obtaining colored surfaces through free-form Gaussian-rendering reconstruction. We train a universal Point-to-Gaussian model to infer the attributes of Gaussian splats for any given pointcloud with merely point coordinates (and color optionally) as input, without requiring any image. Significant technical designs are applied on initialization, regularization and loss functions, making the whole learning process stable. The inferred Gaussian splats can faithfully recover the original appearance of objects or scenes (capable of quick rendering from any viewpoint, like human's imagination ability), meanwhile closely adhering to the input shape. After obtaining a sufficient number of virtually rendered images and depth maps, we employ the truncated signed distance function (TSDF) fusion to get the reconstruction results, producing high-quality and colored meshes. Extensive experiments demonstrate that our approach surpasses state-of-the-art methods in surface reconstruction metrics while maintaining high efficiency and simplicity.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (5) , 3787-3797
GSReuse: Temporally Adaptive Screen-Space Reuse for Accelerating 3D Gaussian Splatting
Recent advances in 3D Gaussian Splatting (3DGS) have enabled real-time, high-fidelity novel view synthesis. However, rendering each frame independently in a video sequence leads to redundant computations, especially when adjacent frames share significant visual overlaps. This inefficiency is particularly problematic in VR applications, where high frame rates and stereoscopic rendering amplify the per-frame cost. Existing frame interpolation or reuse strategies typically rely on image-domain information and are thus not directly applicable to 3DGS rendering, which is fundamentally point-based. To address this runtime inefficiency, we propose GSReuse, a lightweight and drop-in accelerator that speeds up 3DGS rendering by reusing computations across consecutive frames. GSReuse operates in screen space and introduces only minimal modifications to existing 3DGS rendering pipelines. It also eliminates the need for retraining scene representations. Given the rendered image, depth map, and camera parameters of the current frame, GSReuse estimates reliable Gaussian splatting motion vectors for all pixels and warps reusable contents to the new view. A tile-based filtering and masking strategy is then applied to determine which regions can be safely reused, allowing the 3DGS renderer to skip redundant rendering operations. We evaluate GSReuse on multiple benchmark datasets, showing that GSReuse significantly improves rendering, while maintaining high visual fidelity. Compared to state-of-the-art video frame reuse/generation methods, GSReuse delivers better image quality with much lower latency, facilitating practical deployment of 3DGS in VR applications.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (5) , 3787-3797
GSReuse: Temporally Adaptive Screen-Space Reuse for Accelerating 3D Gaussian Splatting
Recent advances in 3D Gaussian Splatting (3DGS) have enabled real-time, high-fidelity novel view synthesis. However, rendering each frame independently in a video sequence leads to redundant computations, especially when adjacent frames share significant visual overlaps. This inefficiency is particularly problematic in VR applications, where high frame rates and stereoscopic rendering amplify the per-frame cost. Existing frame interpolation or reuse strategies typically rely on image-domain information and are thus not directly applicable to 3DGS rendering, which is fundamentally point-based. To address this runtime inefficiency, we propose GSReuse, a lightweight and drop-in accelerator that speeds up 3DGS rendering by reusing computations across consecutive frames. GSReuse operates in screen space and introduces only minimal modifications to existing 3DGS rendering pipelines. It also eliminates the need for retraining scene representations. Given the rendered image, depth map, and camera parameters of the current frame, GSReuse estimates reliable Gaussian splatting motion vectors for all pixels and warps reusable contents to the new view. A tile-based filtering and masking strategy is then applied to determine which regions can be safely reused, allowing the 3DGS renderer to skip redundant rendering operations. We evaluate GSReuse on multiple benchmark datasets, showing that GSReuse significantly improves rendering, while maintaining high visual fidelity. Compared to state-of-the-art video frame reuse/generation methods, GSReuse delivers better image quality with much lower latency, facilitating practical deployment of 3DGS in VR applications.
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Spectral-GS: Taming 3D Gaussian Splatting with Spectral Entropy
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessSpectral-GS: Taming 3D Gaussian Splatting with Spectral Entropy