Ioannis Gkioulekas
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
Ioannis Gkioulekas has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Keenan Crane
Carnegie Mellon University, Pittsburgh, USA
7 shared publications - Bailey Miller
Carnegie Mellon University, Pittsburgh, USA
6 shared publications - Rohan Sawhney
NVIDIA, Santa Clara, USA
5 shared publications - Adithya Pediredla
Dartmouth College, Hanover, USA
3 shared publications - Kavita Bala
Cornell University
3 shared publications - Shuang Zhao
University of Illinois Urbana-Champaign, Urbana, USA
3 shared publications
Latest Publications
- 30 September 2026
- Published by Springer Nature
- p. 1-21
A Second-Order Theory of Texture for Depth from Focus
- 30 September 2026
- Published by Springer Nature
- p. 1-21
A Second-Order Theory of Texture for Depth from Focus
- Open Access
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-24
Points as Tori: Fast Pointwise Signed Distance for Point Clouds
We describe a method for computing signed distance to point clouds that allows fast pointwise evaluation at arbitrary spatial resolution. As input, our method takes a point cloud with normals; as output, it provides an analytical parameterization that allows queries of signed distance to the approximate underlying surface at arbitrary points — simultaneously providing reconstruction and distance. Our key idea is to reconstruct shapes by locally fitting point clouds with tori, which have closed-form signed distance functions. Tori are fitted in a feed-forward manner, using a pre-trained network to output per-point curvature and shift parameters. Importantly, our method does not require costly global optimization or spatial discretization, and is easily parallelizable. Underlying our method is a new theory that unifies signed distance with the classic reconstruction methods of winding numbers and Poisson surface reconstruction. We use our method to compute signed distance to point clouds arising from photogrammetry, meshes, 3D Gaussians, and neural implicits. Our method allows point clouds to be used directly in applications, without explicit surface reconstruction: as examples, we take offsets of point clouds, apply morphological and Boolean operations, and directly visualize offset surfaces using sphere tracing.
- 3 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (4) , 1-24
Open AccessPoints as Tori: Fast Pointwise Signed Distance for Point Clouds
We describe a method for computing signed distance to point clouds that allows fast pointwise evaluation at arbitrary spatial resolution. As input, our method takes a point cloud with normals; as output, it provides an analytical parameterization that allows queries of signed distance to the approximate underlying surface at arbitrary points — simultaneously providing reconstruction and distance. Our key idea is to reconstruct shapes by locally fitting point clouds with tori, which have closed-form signed distance functions. Tori are fitted in a feed-forward manner, using a pre-trained network to output per-point curvature and shift parameters. Importantly, our method does not require costly global optimization or spatial discretization, and is easily parallelizable. Underlying our method is a new theory that unifies signed distance with the classic reconstruction methods of winding numbers and Poisson surface reconstruction. We use our method to compute signed distance to point clouds arising from photogrammetry, meshes, 3D Gaussians, and neural implicits. Our method allows point clouds to be used directly in applications, without explicit surface reconstruction: as examples, we take offsets of point clouds, apply morphological and Boolean operations, and directly visualize offset surfaces using sphere tracing.
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Automated design of compound lenses with discrete-continuous optimization
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessAutomated design of compound lenses with discrete-continuous optimization
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (4) , 1-21
Solving partial differential equations in participating media
We consider the problem of solving partial differential equations (PDEs) in domains with complex microparticle geometry that is impractical, or intractable, to model explicitly. Drawing inspiration from volume rendering, we propose tackling this problem by treating the domain as a participating medium that models microparticle geometry stochastically , through aggregate statistical properties (e.g., particle density). We first introduce the problem setting of PDE simulation in participating media. We then specialize to exponential media and describe the properties that make them an attractive model of microparticle geometry for PDE simulation problems. We use these properties to develop two new algorithms, volumetric walk on spheres and volumetric walk on stars , that generalize previous Monte Carlo algorithms to enable efficient and discretization-free simulation of linear elliptic PDEs (e.g., Laplace) in participating media. We demonstrate experimentally that our algorithms can solve Laplace boundary value problems with complex microparticle geometry more accurately and more efficiently than previous approaches, such as ensemble averaging and homogenization.
- 27 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (4) , 1-21
Open AccessSolving partial differential equations in participating media
We consider the problem of solving partial differential equations (PDEs) in domains with complex microparticle geometry that is impractical, or intractable, to model explicitly. Drawing inspiration from volume rendering, we propose tackling this problem by treating the domain as a participating medium that models microparticle geometry stochastically , through aggregate statistical properties (e.g., particle density). We first introduce the problem setting of PDE simulation in participating media. We then specialize to exponential media and describe the properties that make them an attractive model of microparticle geometry for PDE simulation problems. We use these properties to develop two new algorithms, volumetric walk on spheres and volumetric walk on stars , that generalize previous Monte Carlo algorithms to enable efficient and discretization-free simulation of linear elliptic PDEs (e.g., Laplace) in participating media. We demonstrate experimentally that our algorithms can solve Laplace boundary value problems with complex microparticle geometry more accurately and more efficiently than previous approaches, such as ensemble averaging and homogenization.
- Open Access
Solving partial differential equations in participating media
We consider the problem of solving partial differential equations (PDEs) in domains with complex microparticle geometry that is impractical, or intractable, to model explicitly. Drawing inspiration from volume rendering, we propose tackling this problem by treating the domain as a participating medium that models microparticle geometry stochastically, through aggregate statistical properties (e.g., particle density). We first introduce the problem setting of PDE simulation in participating media. We then specialize to exponential media and describe the properties that make them an attractive model of microparticle geometry for PDE simulation problems. We use these properties to develop two new algorithms, volumetric walk on spheres and volumetric walk on stars, that generalize previous Monte Carlo algorithms to enable efficient and discretization-free simulation of linear elliptic PDEs (e.g., Laplace) in participating media. We demonstrate experimentally that our algorithms can solve Laplace boundary value problems with complex microparticle geometry more accurately and more efficiently than previous approaches, such as ensemble averaging and homogenization.
Open AccessSolving partial differential equations in participating media
We consider the problem of solving partial differential equations (PDEs) in domains with complex microparticle geometry that is impractical, or intractable, to model explicitly. Drawing inspiration from volume rendering, we propose tackling this problem by treating the domain as a participating medium that models microparticle geometry stochastically, through aggregate statistical properties (e.g., particle density). We first introduce the problem setting of PDE simulation in participating media. We then specialize to exponential media and describe the properties that make them an attractive model of microparticle geometry for PDE simulation problems. We use these properties to develop two new algorithms, volumetric walk on spheres and volumetric walk on stars, that generalize previous Monte Carlo algorithms to enable efficient and discretization-free simulation of linear elliptic PDEs (e.g., Laplace) in participating media. We demonstrate experimentally that our algorithms can solve Laplace boundary value problems with complex microparticle geometry more accurately and more efficiently than previous approaches, such as ensemble averaging and homogenization.
- Open Access
- 14 February 2025
- Published by Springer Nature in Communications Engineering
- Vol. 4 (1) , 1-14
Vision-based tactile sensor design using physically based rendering
High-resolution tactile sensors are very helpful to robots for fine-grained perception and manipulation tasks, but designing those sensors is challenging. This is because the designs are based on the compact integration of multiple optical elements, and it is difficult to understand the correlation between the element arrangements and the sensor accuracy by trial and error. In this work, we introduce the digital design of vision-based tactile sensors using a physically accurate light simulator. The framework modularizes the design process, parameterizes the sensor components, and contains an evaluation metric to quantify a sensor’s performance. We quantify the effects of sensor shape, illumination setting, and sensing surface material on tactile sensor performance using our evaluation metric. The proposed optical simulation framework can replicate the tactile image of the real vision-based tactile sensor prototype without any prior sensor-specific data. Using our approach we can substantially improve the design of a fingertip GelSight sensor. This improved design performs approximately 5 times better than previous state-of-the-art human-expert design at real-world robotic tactile embossed text detection. Our simulation approach can be used with any vision-based tactile sensor to produce a physically accurate tactile image. Overall, our approach enables the automatic design of sensorized soft robots and opens the door for closed-loop co-optimization of controllers and sensors for dexterous manipulation.
- 14 February 2025
- Published by Springer Nature in Communications Engineering
- Vol. 4 (1) , 1-14
Open AccessVision-based tactile sensor design using physically based rendering
High-resolution tactile sensors are very helpful to robots for fine-grained perception and manipulation tasks, but designing those sensors is challenging. This is because the designs are based on the compact integration of multiple optical elements, and it is difficult to understand the correlation between the element arrangements and the sensor accuracy by trial and error. In this work, we introduce the digital design of vision-based tactile sensors using a physically accurate light simulator. The framework modularizes the design process, parameterizes the sensor components, and contains an evaluation metric to quantify a sensor’s performance. We quantify the effects of sensor shape, illumination setting, and sensing surface material on tactile sensor performance using our evaluation metric. The proposed optical simulation framework can replicate the tactile image of the real vision-based tactile sensor prototype without any prior sensor-specific data. Using our approach we can substantially improve the design of a fingertip GelSight sensor. This improved design performs approximately 5 times better than previous state-of-the-art human-expert design at real-world robotic tactile embossed text detection. Our simulation approach can be used with any vision-based tactile sensor to produce a physically accurate tactile image. Overall, our approach enables the automatic design of sensorized soft robots and opens the door for closed-loop co-optimization of controllers and sensors for dexterous manipulation.
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (10) , 1-13
Structured light with a million light planes per second
We introduce a structured light system that enables full-frame 3D scanning at speeds of 1000 fps, four times faster than the previous fastest systems. Our key innovation is the use of a custom acousto-optic light scanning device capable of projecting two million light planes per second. Coupling this device with an event camera allows our system to overcome the key bottleneck preventing previous structured light systems based on event cameras from achieving higher scanning speeds-the limited rate of illumination steering. Unlike these previous systems, ours uses the event camera's full-frame bandwidth, shifting the speed bottleneck from the illumination side to the imaging side. To mitigate this new bottleneck and further increase scanning speed, we introduce adaptive scanning strategies that leverage the event camera's asynchronous operation by selectively illuminating regions of interest, thereby achieving effective scanning speeds an order of magnitude beyond the camera's theoretical limit.
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (10) , 1-13
Structured light with a million light planes per second
We introduce a structured light system that enables full-frame 3D scanning at speeds of 1000 fps, four times faster than the previous fastest systems. Our key innovation is the use of a custom acousto-optic light scanning device capable of projecting two million light planes per second. Coupling this device with an event camera allows our system to overcome the key bottleneck preventing previous structured light systems based on event cameras from achieving higher scanning speeds-the limited rate of illumination steering. Unlike these previous systems, ours uses the event camera's full-frame bandwidth, shifting the speed bottleneck from the illumination side to the imaging side. To mitigate this new bottleneck and further increase scanning speed, we introduce adaptive scanning strategies that leverage the event camera's asynchronous operation by selectively illuminating regions of interest, thereby achieving effective scanning speeds an order of magnitude beyond the camera's theoretical limit.
- Open Access
- 19 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (6) , 1-18
Differential Walk on Spheres
We introduce a Monte Carlo method for computing derivatives of the solution to a partial differential equation (PDE) with respect to problem parameters (such as domain geometry or boundary conditions). Derivatives can be evaluated at arbitrary points, without performing a global solve or constructing a volumetric grid or mesh. The method is hence well suited to inverse problems with complex geometry, such as PDE-constrained shape optimization. Like other walk on spheres (WoS) algorithms, our method is trivial to parallelize, and is agnostic to boundary representation (meshes, splines, implicit surfaces, etc. ), supporting large topological changes. We focus in particular on screened Poisson equations, which model diverse problems from scientific and geometric computing. As in differentiable rendering, we jointly estimate derivatives with respect to all parameters---hence, cost does not grow significantly with parameter count. In practice, even noisy derivative estimates exhibit fast, stable convergence for stochastic gradient-based optimization, as we show through examples from thermal design, shape from diffusion, and computer graphics.
- 19 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (6) , 1-18
Open AccessDifferential Walk on Spheres
We introduce a Monte Carlo method for computing derivatives of the solution to a partial differential equation (PDE) with respect to problem parameters (such as domain geometry or boundary conditions). Derivatives can be evaluated at arbitrary points, without performing a global solve or constructing a volumetric grid or mesh. The method is hence well suited to inverse problems with complex geometry, such as PDE-constrained shape optimization. Like other walk on spheres (WoS) algorithms, our method is trivial to parallelize, and is agnostic to boundary representation (meshes, splines, implicit surfaces, etc. ), supporting large topological changes. We focus in particular on screened Poisson equations, which model diverse problems from scientific and geometric computing. As in differentiable rendering, we jointly estimate derivatives with respect to all parameters---hence, cost does not grow significantly with parameter count. In practice, even noisy derivative estimates exhibit fast, stable convergence for stochastic gradient-based optimization, as we show through examples from thermal design, shape from diffusion, and computer graphics.
- Open Access
- 19 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (6) , 1-19
3D Reconstruction with Fast Dipole Sums
We introduce a method for high-quality 3D reconstruction from multi-view images. Our method uses a new point-based representation, the regularized dipole sum, which generalizes the winding number to allow for interpolation of per-point attributes in point clouds with noisy or outlier points. Using regularized dipole sums, we represent implicit geometry and radiance fields as per-point attributes of a dense point cloud, which we initialize from structure from motion. We additionally derive Barnes-Hut fast summation schemes for accelerated forward and adjoint dipole sum queries. These queries facilitate the use of ray tracing to efficiently and differentiably render images with our point-based representations, and thus update their point attributes to optimize scene geometry and appearance. We evaluate our method in inverse rendering applications against state-of-the-art alternatives, based on ray tracing of neural representations or rasterization of Gaussian point-based representations. Our method significantly improves 3D reconstruction quality and robustness at equal runtimes, while also supporting more general rendering methods such as shadow rays for direct illumination.
- 19 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (6) , 1-19
Open Access3D Reconstruction with Fast Dipole Sums
We introduce a method for high-quality 3D reconstruction from multi-view images. Our method uses a new point-based representation, the regularized dipole sum, which generalizes the winding number to allow for interpolation of per-point attributes in point clouds with noisy or outlier points. Using regularized dipole sums, we represent implicit geometry and radiance fields as per-point attributes of a dense point cloud, which we initialize from structure from motion. We additionally derive Barnes-Hut fast summation schemes for accelerated forward and adjoint dipole sum queries. These queries facilitate the use of ray tracing to efficiently and differentiably render images with our point-based representations, and thus update their point attributes to optimize scene geometry and appearance. We evaluate our method in inverse rendering applications against state-of-the-art alternatives, based on ray tracing of neural representations or rasterization of Gaussian point-based representations. Our method significantly improves 3D reconstruction quality and robustness at equal runtimes, while also supporting more general rendering methods such as shadow rays for direct illumination.
- Top Cited PapersOpen Access
- 19 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (4) , 1-18
Walkin’ Robin: Walk on Stars with Robin Boundary Conditions
Numerous scientific and engineering applications require solutions to boundary value problems (BVPs) involving elliptic partial differential equations, such as the Laplace or Poisson equations, on geometrically intricate domains. We develop a Monte Carlo method for solving such BVPs with arbitrary first-order linear boundary conditions---Dirichlet, Neumann, and Robin. Our method directly generalizes the walk on stars (WoSt) algorithm, which previously tackled only the first two types of boundary conditions, with a few simple modifications. Unlike conventional numerical methods, WoSt does not need finite element meshing or global solves. Similar to Monte Carlo rendering, it instead computes pointwise solution estimates by simulating random walks along star-shaped regions inside the BVP domain, using efficient ray-intersection and distance queries. To ensure WoSt produces bounded-variance estimates in the presence of Robin boundary conditions, we show that it is sufficient to modify how WoSt selects the size of these star-shaped regions. Our generalized WoSt algorithm reduces estimation error by orders of magnitude relative to alternative grid-free methods such as the walk on boundary algorithm. We also develop bidirectional and boundary value caching strategies to further reduce estimation error. Our algorithm is trivial to parallelize, scales sublinearly with increasing geometric detail, and enables progressive and view-dependent evaluation.
- 19 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (4) , 1-18
Top Cited PapersOpen AccessWalkin’ Robin: Walk on Stars with Robin Boundary Conditions
Numerous scientific and engineering applications require solutions to boundary value problems (BVPs) involving elliptic partial differential equations, such as the Laplace or Poisson equations, on geometrically intricate domains. We develop a Monte Carlo method for solving such BVPs with arbitrary first-order linear boundary conditions---Dirichlet, Neumann, and Robin. Our method directly generalizes the walk on stars (WoSt) algorithm, which previously tackled only the first two types of boundary conditions, with a few simple modifications. Unlike conventional numerical methods, WoSt does not need finite element meshing or global solves. Similar to Monte Carlo rendering, it instead computes pointwise solution estimates by simulating random walks along star-shaped regions inside the BVP domain, using efficient ray-intersection and distance queries. To ensure WoSt produces bounded-variance estimates in the presence of Robin boundary conditions, we show that it is sufficient to modify how WoSt selects the size of these star-shaped regions. Our generalized WoSt algorithm reduces estimation error by orders of magnitude relative to alternative grid-free methods such as the walk on boundary algorithm. We also develop bidirectional and boundary value caching strategies to further reduce estimation error. Our algorithm is trivial to parallelize, scales sublinearly with increasing geometric detail, and enables progressive and view-dependent evaluation.