Leif Kobbelt
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
Leif Kobbelt has a total of 159 co-authors. Here are the top co-authors by number of shared publications:
- Marcel Campen
Paderborn University Germany
7 shared publications - David Bommes
University of Bern, Bern, Switzerland
5 shared publications - Philip Trettner
RWTH Aachen University Germany
5 shared publications - Yu-Kun Lai
Cardiff University, United Kingdom
5 shared publications - Lin Gao
University of Chinese Academy of Sciences, Beijing, China
4 shared publications - Patrick Schmidt
RWTH Aachen University Germany
4 shared publications
Latest Publications
- Open Access
- 16 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
- Vol. 8 (1) , 1-5
The Challenge of Multi-Organ Crosstalk Research
The prevalence of multimorbid patients (i.e., one person with two or more diseases) is critical for patients, medical doctors, and society alike since it complicates treatment and results in high (treatment) costs. However, contemporary medicine mainly specializes in single-organ approaches, frequently overlooking the interactions between different organs causing multimorbidities. Recent research on bilateral organ crosstalk (OCT) reveals the complex interplay between organs and the importance of studying OCT, especially involving more than two organs. Tackling the challenges associated with multi-OCT requires fundamental methodological advances in computer science, specifically related to handling multi-modal data, the combinatorial explosion of complexity, and data sensitivity. Thus, research should generally be directed toward (i) methods for identifying affected organs, (ii) concepts for discovering disease progression, and (iii) models for validation in clinical studies. When addressing these challenges interdisciplinarily, computer science and medicine will jointly improve the understanding of OCT and multimorbidity, resulting in novel treatment options for multimorbid patients, reduced healthcare costs, and broad benefits for society.
- 16 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
- Vol. 8 (1) , 1-5
Open AccessThe Challenge of Multi-Organ Crosstalk Research
The prevalence of multimorbid patients (i.e., one person with two or more diseases) is critical for patients, medical doctors, and society alike since it complicates treatment and results in high (treatment) costs. However, contemporary medicine mainly specializes in single-organ approaches, frequently overlooking the interactions between different organs causing multimorbidities. Recent research on bilateral organ crosstalk (OCT) reveals the complex interplay between organs and the importance of studying OCT, especially involving more than two organs. Tackling the challenges associated with multi-OCT requires fundamental methodological advances in computer science, specifically related to handling multi-modal data, the combinatorial explosion of complexity, and data sensitivity. Thus, research should generally be directed toward (i) methods for identifying affected organs, (ii) concepts for discovering disease progression, and (iii) models for validation in clinical studies. When addressing these challenges interdisciplinarily, computer science and medicine will jointly improve the understanding of OCT and multimorbidity, resulting in novel treatment options for multimorbid patients, reduced healthcare costs, and broad benefits for society.
- Open Access
- 30 April 2026
- Published by Wiley in Computer Graphics Forum
Embedding Optimization of Layouts via Distortion Minimization
Given an embedding of a layout in the surface of a target mesh, we consider the problem of optimizing the embedding geometrically. Layout embeddings partition the surface into multiple disk‐like patches, making them particularly useful for parametrization and remeshing tasks, such as quad‐remeshing, since these problems can then be solved on simpler subdomains. Existing methods can either not guarantee to maintain patch connectivity, limiting downstream applications, or are specialized for quad layout optimization, relying on principal curvature information. We propose a framework that balances per‐patch distortion minimization with strict connectivity control through an explicit representation. By inserting additional nodes along layout arcs, they can be embedded as piecewise geodesic curves on the surface. This sampling of arcs provides additional flexibility where required, enabling joint optimization of both node positions and arc embeddings. Our representation naturally supports a multi‐resolution workflow: optimization on coarse meshes can be prolongated to high‐resolution inputs. We demonstrate its effectiveness in applications requiring connectivity‐preserving, low‐distortion surface layouts. Code will be available at https://github.com/7‐AlexH/layout‐embedding‐optimization.
- 30 April 2026
- Published by Wiley in Computer Graphics Forum
Open AccessEmbedding Optimization of Layouts via Distortion Minimization
Given an embedding of a layout in the surface of a target mesh, we consider the problem of optimizing the embedding geometrically. Layout embeddings partition the surface into multiple disk‐like patches, making them particularly useful for parametrization and remeshing tasks, such as quad‐remeshing, since these problems can then be solved on simpler subdomains. Existing methods can either not guarantee to maintain patch connectivity, limiting downstream applications, or are specialized for quad layout optimization, relying on principal curvature information. We propose a framework that balances per‐patch distortion minimization with strict connectivity control through an explicit representation. By inserting additional nodes along layout arcs, they can be embedded as piecewise geodesic curves on the surface. This sampling of arcs provides additional flexibility where required, enabling joint optimization of both node positions and arc embeddings. Our representation naturally supports a multi‐resolution workflow: optimization on coarse meshes can be prolongated to high‐resolution inputs. We demonstrate its effectiveness in applications requiring connectivity‐preserving, low‐distortion surface layouts. Code will be available at https://github.com/7‐AlexH/layout‐embedding‐optimization.
- Open Access
- 25 April 2026
- Published by Wiley in Computer Graphics Forum
Self‐supervised Learning of Fine‐to‐Coarse Cuboid Shape Abstraction
The abstraction of 3D objects with simple geometric primitives like cuboids allows us to infer structural information from complex geometry. It is important for 3D shape understanding, structural analysis and geometric modeling. We introduce a novel fine‐to‐coarse self‐supervised learning approach to abstract collections of 3D shapes. Our architectural design allows us to reduce the number of primitives from hundreds (fine reconstruction) to only a few (coarse abstraction) during training. This allows our network to optimize the reconstruction error and adhere to a user‐specified number of primitives per shape while simultaneously learning a consistent structure across the whole collection of data. We achieve this through our abstraction loss formulation which increasingly penalizes redundant primitives. Furthermore, we introduce a reconstruction loss formulation to account not only for surface approximation but also volume preservation. Combining both contributions allows us to represent 3D shapes more precisely with fewer cuboid primitives than previous work. We evaluate our method on collections of man‐made and humanoid shapes comparing with previous state‐of‐the‐art learning methods on commonly used benchmarks. Our results confirm an improvement over previous cuboid‐based shape abstraction techniques. Furthermore, we demonstrate our cuboid abstraction in downstream tasks like clustering, retrieval, and partial symmetry detection.
- 25 April 2026
- Published by Wiley in Computer Graphics Forum
Open AccessSelf‐supervised Learning of Fine‐to‐Coarse Cuboid Shape Abstraction
The abstraction of 3D objects with simple geometric primitives like cuboids allows us to infer structural information from complex geometry. It is important for 3D shape understanding, structural analysis and geometric modeling. We introduce a novel fine‐to‐coarse self‐supervised learning approach to abstract collections of 3D shapes. Our architectural design allows us to reduce the number of primitives from hundreds (fine reconstruction) to only a few (coarse abstraction) during training. This allows our network to optimize the reconstruction error and adhere to a user‐specified number of primitives per shape while simultaneously learning a consistent structure across the whole collection of data. We achieve this through our abstraction loss formulation which increasingly penalizes redundant primitives. Furthermore, we introduce a reconstruction loss formulation to account not only for surface approximation but also volume preservation. Combining both contributions allows us to represent 3D shapes more precisely with fewer cuboid primitives than previous work. We evaluate our method on collections of man‐made and humanoid shapes comparing with previous state‐of‐the‐art learning methods on commonly used benchmarks. Our results confirm an improvement over previous cuboid‐based shape abstraction techniques. Furthermore, we demonstrate our cuboid abstraction in downstream tasks like clustering, retrieval, and partial symmetry detection.
- Open Access
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-15
CrossGen: Learning and Generating Cross Fields for Quad Meshing
Cross fields play a critical role in various geometry processing tasks, especially for quad mesh generation. Existing methods for cross field generation often struggle to balance computational efficiency with generation quality, using slow per-shape optimization. We introduce CrossGen , a novel framework that supports both feed-forward prediction and latent generative modeling of cross fields for quad meshing by unifying geometry and cross field representations within a joint latent space. Our method enables extremely fast computation of high-quality cross fields of general input shapes, typically within one second without per-shape optimization. Our method assumes a point-sampled surface, also called a point-cloud surface , as input, so we can accommodate various surface representations by a straightforward point sampling process. Using an auto-encoder network architecture, we encode input point-cloud surfaces into a sparse voxel grid with fine-grained latent spaces, which are decoded into both SDF-based surface geometry and cross fields (see the teaser figure). We also contribute a dataset of models with both high-quality signed distance fields (SDFs) representations and their corresponding cross fields, and use it to train our network. Once trained, the network is capable of computing a cross field of an input surface in a feed-forward manner, ensuring high geometric fidelity, noise resilience, and rapid inference. Furthermore, leveraging the same unified latent representation, we incorporate a diffusion model for computing cross fields of new shapes generated from partial input, such as sketches. To demonstrate its practical applications, we validate CrossGen on the quad mesh generation task for a large variety of surface shapes. Experimental results demonstrate that CrossGen generalizes well across diverse shapes and consistently yields high-fidelity cross fields, thus facilitating the generation of high-quality quad meshes.
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (6) , 1-15
Open AccessCrossGen: Learning and Generating Cross Fields for Quad Meshing
Cross fields play a critical role in various geometry processing tasks, especially for quad mesh generation. Existing methods for cross field generation often struggle to balance computational efficiency with generation quality, using slow per-shape optimization. We introduce CrossGen , a novel framework that supports both feed-forward prediction and latent generative modeling of cross fields for quad meshing by unifying geometry and cross field representations within a joint latent space. Our method enables extremely fast computation of high-quality cross fields of general input shapes, typically within one second without per-shape optimization. Our method assumes a point-sampled surface, also called a point-cloud surface , as input, so we can accommodate various surface representations by a straightforward point sampling process. Using an auto-encoder network architecture, we encode input point-cloud surfaces into a sparse voxel grid with fine-grained latent spaces, which are decoded into both SDF-based surface geometry and cross fields (see the teaser figure). We also contribute a dataset of models with both high-quality signed distance fields (SDFs) representations and their corresponding cross fields, and use it to train our network. Once trained, the network is capable of computing a cross field of an input surface in a feed-forward manner, ensuring high geometric fidelity, noise resilience, and rapid inference. Furthermore, leveraging the same unified latent representation, we incorporate a diffusion model for computing cross fields of new shapes generated from partial input, such as sketches. To demonstrate its practical applications, we validate CrossGen on the quad mesh generation task for a large variety of surface shapes. Experimental results demonstrate that CrossGen generalizes well across diverse shapes and consistently yields high-fidelity cross fields, thus facilitating the generation of high-quality quad meshes.
- 28 August 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (5)
Exact and Efficient Mesh‐Kernel Generation
The mesh kernel for a star‐shaped mesh is a convex polyhedron given by the intersection of all half‐spaces defined by the faces of the input mesh. For all non‐star‐shaped meshes, the kernel is empty. We present a method to robustly and efficiently compute the kernel of an input triangle mesh by using exact plane‐based integer arithmetic to compute the mesh kernel. We make use of several ways to accelerate the computation time. Since many applications just require information if a non‐empty mesh kernel exists, we also propose a method to efficiently determine whether a kernel exists by developing an exact plane‐based linear program solver. We evaluate our method on a large dataset of triangle meshes and show that in contrast to previous methods, our approach is exact and robust while maintaining a high performance. It is on average two orders of magnitude faster than other exact state‐of‐the‐art methods and often about one order of magnitude faster than non‐exact methods.
- 28 August 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (5)
Exact and Efficient Mesh‐Kernel Generation
The mesh kernel for a star‐shaped mesh is a convex polyhedron given by the intersection of all half‐spaces defined by the faces of the input mesh. For all non‐star‐shaped meshes, the kernel is empty. We present a method to robustly and efficiently compute the kernel of an input triangle mesh by using exact plane‐based integer arithmetic to compute the mesh kernel. We make use of several ways to accelerate the computation time. Since many applications just require information if a non‐empty mesh kernel exists, we also propose a method to efficiently determine whether a kernel exists by developing an exact plane‐based linear program solver. We evaluate our method on a large dataset of triangle meshes and show that in contrast to previous methods, our approach is exact and robust while maintaining a high performance. It is on average two orders of magnitude faster than other exact state‐of‐the‐art methods and often about one order of magnitude faster than non‐exact methods.
- Top Cited Papers
- 14 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (8) , 6307-6319
DeferredGS: Decoupled and Relightable Gaussian Splatting With Deferred Shading
Reconstructing and editing 3D objects and scenes both play crucial roles in computer graphics and computer vision. Neural radiance fields (NeRFs) can achieve realistic reconstruction and editing results but suffer from inefficiency in rendering. Gaussian splatting significantly accelerates rendering by rasterizing Gaussian ellipsoids. However, Gaussian splatting utilizes a single Spherical Harmonic (SH) function to model both texture and lighting, limiting independent editing capabilities of these components. Recently, attempts have been made to decouple texture and lighting with the Gaussian splatting representation but may fail to produce plausible geometry and decomposition results on reflective scenes. Additionally, the forward shading technique they employ introduces noticeable blending artifacts during relighting, as the geometry attributes of Gaussians are optimized under the original illumination and may not be suitable for novel lighting conditions. To address these issues, we introduce DeferredGS, a method for decoupling and relighting the Gaussian splatting representation using deferred shading. To achieve successful decoupling, we model the illumination with a learnable environment map and define additional attributes such as texture parameters and normal direction on Gaussians, where the normal is distilled from a jointly trained signed distance function. More importantly, we apply deferred shading, resulting in more realistic relighting effects compared to previous methods. Both qualitative and quantitative experiments demonstrate the superior performance of DeferredGSin novel view synthesis and relighting tasks.
- 14 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (8) , 6307-6319
Top Cited PapersDeferredGS: Decoupled and Relightable Gaussian Splatting With Deferred Shading
Reconstructing and editing 3D objects and scenes both play crucial roles in computer graphics and computer vision. Neural radiance fields (NeRFs) can achieve realistic reconstruction and editing results but suffer from inefficiency in rendering. Gaussian splatting significantly accelerates rendering by rasterizing Gaussian ellipsoids. However, Gaussian splatting utilizes a single Spherical Harmonic (SH) function to model both texture and lighting, limiting independent editing capabilities of these components. Recently, attempts have been made to decouple texture and lighting with the Gaussian splatting representation but may fail to produce plausible geometry and decomposition results on reflective scenes. Additionally, the forward shading technique they employ introduces noticeable blending artifacts during relighting, as the geometry attributes of Gaussians are optimized under the original illumination and may not be suitable for novel lighting conditions. To address these issues, we introduce DeferredGS, a method for decoupling and relighting the Gaussian splatting representation using deferred shading. To achieve successful decoupling, we model the illumination with a learnable environment map and define additional attributes such as texture parameters and normal direction on Gaussians, where the normal is distilled from a jointly trained signed distance function. More importantly, we apply deferred shading, resulting in more realistic relighting effects compared to previous methods. Both qualitative and quantitative experiments demonstrate the superior performance of DeferredGSin novel view synthesis and relighting tasks.
- Open Access
- 19 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (6) , 1-22
Surface Reconstruction Using Rotation Systems
Inspired by the seminal result that a graph and an associated rotation system uniquely determine the topology of a closed manifold, we propose a combinatorial method for reconstruction of surfaces from points. Our method constructs a spanning tree and a rotation system. Since the tree is trivially a planar graph, its rotation system determines a genus zero surface with a single face which we proceed to incrementally refine by inserting edges to split faces. In order to raise the genus, special handles are added in a later stage by inserting edges between different faces and thus merging them. We apply our method to a wide range of input point clouds in order to investigate its effectiveness, and we compare our method to several other surface reconstruction methods. It turns out that our approach has two specific benefits over these other methods. First, the output mesh preserves the most information from the input point cloud. Second, our method provides control over the topology of the reconstructed surface. Code is available on https://github.com/cuirq3/RsR.
- 19 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (6) , 1-22
Open AccessSurface Reconstruction Using Rotation Systems
Inspired by the seminal result that a graph and an associated rotation system uniquely determine the topology of a closed manifold, we propose a combinatorial method for reconstruction of surfaces from points. Our method constructs a spanning tree and a rotation system. Since the tree is trivially a planar graph, its rotation system determines a genus zero surface with a single face which we proceed to incrementally refine by inserting edges to split faces. In order to raise the genus, special handles are added in a later stage by inserting edges between different faces and thus merging them. We apply our method to a wide range of input point clouds in order to investigate its effectiveness, and we compare our method to several other surface reconstruction methods. It turns out that our approach has two specific benefits over these other methods. First, the output mesh preserves the most information from the input point cloud. Second, our method provides control over the topology of the reconstructed surface. Code is available on https://github.com/cuirq3/RsR.
- 31 October 2024
- Published by Springer Nature
- p. 271-288
Retargeting Visual Data with Deformation Fields
- 31 October 2024
- Published by Springer Nature
- p. 271-288
Retargeting Visual Data with Deformation Fields
- Open Access
- 27 April 2024
- Published by Wiley in Computer Graphics Forum
- Vol. 43 (2)
Freeform Shape Fabrication by Kerfing Stiff Materials
Fast, flexible, and cost efficient production of 3D models from 2D material sheets is a key component in digital fabrication and prototyping. In order to achieve high quality approximations of freeform shapes, a common set of methods aim to produce bendable 2D cutouts that are then assembled. So far bent surfaces are achieved automatically by computing developable patches of the input surface, e.g. in the context of papercraft. For stiff materials such as medium‐density fibreboard (MDF) or plywood, the 2D cutouts require the application of additional cutting patterns (“kerfing”) to make them bendable. Such kerf patterns are commonly constructed with considerable user input, e.g. in architectural design. We propose a fully automatic method that produces kerfed cutouts suitable for the assembly of freeform shapes from stiff material sheets. By exploring the degrees of freedom emerging from the choice of bending directions, the creation of box joints at the patch boundaries as well as the application of kerf cuts with adaptive density, our method is able to achieve a high quality approximation of the input.
- 27 April 2024
- Published by Wiley in Computer Graphics Forum
- Vol. 43 (2)
Open AccessFreeform Shape Fabrication by Kerfing Stiff Materials
Fast, flexible, and cost efficient production of 3D models from 2D material sheets is a key component in digital fabrication and prototyping. In order to achieve high quality approximations of freeform shapes, a common set of methods aim to produce bendable 2D cutouts that are then assembled. So far bent surfaces are achieved automatically by computing developable patches of the input surface, e.g. in the context of papercraft. For stiff materials such as medium‐density fibreboard (MDF) or plywood, the 2D cutouts require the application of additional cutting patterns (“kerfing”) to make them bendable. Such kerf patterns are commonly constructed with considerable user input, e.g. in architectural design. We propose a fully automatic method that produces kerfed cutouts suitable for the assembly of freeform shapes from stiff material sheets. By exploring the degrees of freedom emerging from the choice of bending directions, the creation of box joints at the patch boundaries as well as the application of kerf cuts with adaptive density, our method is able to achieve a high quality approximation of the input.
- 15 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 14821-14837
Interactive NeRF Geometry Editing With Shape Priors
Neural Radiance Fields (NeRFs) have shown great potential for tasks like novel view synthesis of static 3D scenes. Since NeRFs are trained on a large number of input images, it is not trivial to change their content afterwards. Previous methods to modify NeRFs provide some control but they do not support direct shape deformation which is common for geometry representations like triangle meshes. In this paper, we present a NeRF geometry editing method that first extracts a triangle mesh representation of the geometry inside a NeRF. This mesh can be modified by any 3D modeling tool (we use ARAP mesh deformation). The mesh deformation is then extended into a volume deformation around the shape which establishes a mapping between ray queries to the deformed NeRF and the corresponding queries to the original NeRF. The basic shape editing mechanism is extended towards more powerful and more meaningful editing handles by generating box abstractions of the NeRF shapes which provide an intuitive interface to the user. By additionally assigning semantic labels, we can even identify and combine parts from different objects. We demonstrate the performance and quality of our method in a number of experiments on synthetic data as well as real captured scenes.
- 15 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (12) , 14821-14837
Interactive NeRF Geometry Editing With Shape Priors
Neural Radiance Fields (NeRFs) have shown great potential for tasks like novel view synthesis of static 3D scenes. Since NeRFs are trained on a large number of input images, it is not trivial to change their content afterwards. Previous methods to modify NeRFs provide some control but they do not support direct shape deformation which is common for geometry representations like triangle meshes. In this paper, we present a NeRF geometry editing method that first extracts a triangle mesh representation of the geometry inside a NeRF. This mesh can be modified by any 3D modeling tool (we use ARAP mesh deformation). The mesh deformation is then extended into a volume deformation around the shape which establishes a mapping between ray queries to the deformed NeRF and the corresponding queries to the original NeRF. The basic shape editing mechanism is extended towards more powerful and more meaningful editing handles by generating box abstractions of the NeRF shapes which provide an intuitive interface to the user. By additionally assigning semantic labels, we can even identify and combine parts from different objects. We demonstrate the performance and quality of our method in a number of experiments on synthetic data as well as real captured scenes.