Jon Hasselgren
Research Subjects
Research Interests
Jon Hasselgren has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Jacob Munkberg
NVIDIA, Lund, Sweden
5 shared publications - Jacob Munkberg
NVIDIA
2 shared publications - Zian Wang
Nvidia, Toronto, Canada
2 shared publications - Aaron Lefohn
NVIDIA, Redmond, USA
1 shared publication - Andrea Weidlich
NVIDIA, Montreal, Canada
1 shared publication - Anjul Patney
NVIDIA
1 shared publication
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Toward Richer Material Generation via Procedural Data Enhancement
Generative models for material creation are fundamentally limited by the quality and expressivity of available training data. Simple physically based rendering (PBR) materials, which combine a diffuse term with a single-lobe specular component, are commonly used for training but are insufficient to capture many important visual effects present in real materials. We present a method that enhances such simple PBR materials to more expressive ones, by augmenting the single GGX specular lobe into a layered model that captures a broader range of non-diffuse effects. Starting from a simple material, we procedurally construct a corresponding multi-lobe non-diffuse component guided by physical priors, enabling effects such as dust, clearcoat, and layered scattering. To provide a compact representation for downstream applications, we encode this non-diffuse component as a neural material with a shared 6D latent space, where each material instance is represented by two latent textures and decoded by a pretrained universal MLP. We further regularize the latent space to support material generation. The resulting neural material dataset enables training generative models for richer material creation. To demonstrate this application, we finetune a video diffusion model to produce neural latent textures that encode our multi-lobe material, and present generative results as proof of feasibility. Our procedural data enhancement approach is an important step toward improving expressivity in material generation.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessToward Richer Material Generation via Procedural Data Enhancement
Generative models for material creation are fundamentally limited by the quality and expressivity of available training data. Simple physically based rendering (PBR) materials, which combine a diffuse term with a single-lobe specular component, are commonly used for training but are insufficient to capture many important visual effects present in real materials. We present a method that enhances such simple PBR materials to more expressive ones, by augmenting the single GGX specular lobe into a layered model that captures a broader range of non-diffuse effects. Starting from a simple material, we procedurally construct a corresponding multi-lobe non-diffuse component guided by physical priors, enabling effects such as dust, clearcoat, and layered scattering. To provide a compact representation for downstream applications, we encode this non-diffuse component as a neural material with a shared 6D latent space, where each material instance is represented by two latent textures and decoded by a pretrained universal MLP. We further regularize the latent space to support material generation. The resulting neural material dataset enables training generative models for richer material creation. To demonstrate this application, we finetune a video diffusion model to produce neural latent textures that encode our multi-lobe material, and present generative results as proof of feasibility. Our procedural data enhancement approach is an important step toward improving expressivity in material generation.
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Generative detail enhancement for physically based materials
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessGenerative detail enhancement for physically based materials
- 24 July 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (4)
VideoMat: Extracting PBR Materials from Video Diffusion Models
We leverage finetuned video diffusion models, intrinsic decomposition of videos, and physically‐based differentiable rendering to generate high quality materials for 3D models given a text prompt or a single image. We condition a video diffusion model to respect the input geometry and lighting condition. This model produces multiple views of a given 3D model with coherent material properties. Secondly, we use a recent model to extract intrinsics (base color, roughness, metallic) from the generated video. Finally, we use the intrinsics alongside the generated video in a differentiable path tracer to robustly extract PBR materials directly compatible with common content creation tools.
- 24 July 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (4)
VideoMat: Extracting PBR Materials from Video Diffusion Models
We leverage finetuned video diffusion models, intrinsic decomposition of videos, and physically‐based differentiable rendering to generate high quality materials for 3D models given a text prompt or a single image. We condition a video diffusion model to respect the input geometry and lighting condition. This model produces multiple views of a given 3D model with coherent material properties. Secondly, we use a recent model to extract intrinsics (base color, roughness, metallic) from the generated video. Finally, we use the intrinsics alongside the generated video in a differentiable path tracer to robustly extract PBR materials directly compatible with common content creation tools.
- Top Cited PapersOpen Access
- 26 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (4) , 1-16
Flexible Isosurface Extraction for Gradient-Based Mesh Optimization
This work considers gradient-based mesh optimization, where we iteratively optimize for a 3D surface mesh by representing it as the isosurface of a scalar field, an increasingly common paradigm in applications including photogrammetry, generative modeling, and inverse physics. Existing implementations adapt classic isosurface extraction algorithms like Marching Cubes or Dual Contouring; these techniques were designed to extract meshes from fixed, known fields, and in the optimization setting they lack the degrees of freedom to represent high-quality feature-preserving meshes, or suffer from numerical instabilities. We introduce FlexiCubes, an isosurface representation specifically designed for optimizing an unknown mesh with respect to geometric, visual, or even physical objectives. Our main insight is to introduce additional carefully-chosen parameters into the representation, which allow local flexible adjustments to the extracted mesh geometry and connectivity. These parameters are updated along with the underlying scalar field via automatic differentiation when optimizing for a downstream task. We base our extraction scheme on Dual Marching Cubes for improved topological properties, and present extensions to optionally generate tetrahedral and hierarchically-adaptive meshes. Extensive experiments validate FlexiCubes on both synthetic benchmarks and real-world applications, showing that it offers significant improvements in mesh quality and geometric fidelity.
- 26 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (4) , 1-16
Top Cited PapersOpen AccessFlexible Isosurface Extraction for Gradient-Based Mesh Optimization
This work considers gradient-based mesh optimization, where we iteratively optimize for a 3D surface mesh by representing it as the isosurface of a scalar field, an increasingly common paradigm in applications including photogrammetry, generative modeling, and inverse physics. Existing implementations adapt classic isosurface extraction algorithms like Marching Cubes or Dual Contouring; these techniques were designed to extract meshes from fixed, known fields, and in the optimization setting they lack the degrees of freedom to represent high-quality feature-preserving meshes, or suffer from numerical instabilities. We introduce FlexiCubes, an isosurface representation specifically designed for optimizing an unknown mesh with respect to geometric, visual, or even physical objectives. Our main insight is to introduce additional carefully-chosen parameters into the representation, which allow local flexible adjustments to the extracted mesh geometry and connectivity. These parameters are updated along with the underlying scalar field via automatic differentiation when optimizing for a downstream task. We base our extraction scheme on Dual Marching Cubes for improved topological properties, and present extensions to optionally generate tetrahedral and hierarchically-adaptive meshes. Extensive experiments validate FlexiCubes on both synthetic benchmarks and real-world applications, showing that it offers significant improvements in mesh quality and geometric fidelity.
- Open Access
- 12 May 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Computer Graphics and Interactive Techniques
- Vol. 6 (1) , 1-16
Joint Neural Denoising of Surfaces and Volumes
Denoisers designed for surface geometry rely on noise-free feature guides for high quality results. However, these guides are not readily available for volumes. Our method enables combined volume and surface denoising in real time from low sample count (4 spp) renderings. The rendered image is decomposed into volume and surface layers, leveraging spatio-temporal neural denoisers for both components. The individual signals are composited using learned weights and denoised transmittance. Our architecture outperforms current denoisers in scenes containing both surfaces and volumes, and produces temporally stable results at interactive rates.
- 12 May 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Computer Graphics and Interactive Techniques
- Vol. 6 (1) , 1-16
Open AccessJoint Neural Denoising of Surfaces and Volumes
Denoisers designed for surface geometry rely on noise-free feature guides for high quality results. However, these guides are not readily available for volumes. Our method enables combined volume and surface denoising in real time from low sample count (4 spp) renderings. The rendered image is decomposed into volume and surface layers, leveraging spatio-temporal neural denoisers for both components. The individual signals are composited using learned weights and denoised transmittance. Our architecture outperforms current denoisers in scenes containing both surfaces and volumes, and produces temporally stable results at interactive rates.
- 20 July 2020
- Published by Wiley in Computer Graphics Forum
- Vol. 39 (4) , 1-12
Neural Denoising with Layer Embeddings
We propose a novel approach for denoising Monte Carlo path traced images, which uses data from individual samples rather than relying on pixel aggregates. Samples are partitioned into layers, which are filtered separately, giving the network more freedom to handle outliers and complex visibility. Finally the layers are composited front‐to‐back using alpha blending. The system is trained end‐to‐end, with learned layer partitioning, filter kernels, and compositing. We obtain similar image quality as recent state‐of‐the‐art sample based denoisers at a fraction of the computational cost and memory requirements.
- 20 July 2020
- Published by Wiley in Computer Graphics Forum
- Vol. 39 (4) , 1-12
Neural Denoising with Layer Embeddings
We propose a novel approach for denoising Monte Carlo path traced images, which uses data from individual samples rather than relying on pixel aggregates. Samples are partitioned into layers, which are filtered separately, giving the network more freedom to handle outliers and complex visibility. Finally the layers are composited front‐to‐back using alpha blending. The system is trained end‐to‐end, with learned layer partitioning, filter kernels, and compositing. We obtain similar image quality as recent state‐of‐the‐art sample based denoisers at a fraction of the computational cost and memory requirements.
- 1 May 2020
- Published by Wiley in Computer Graphics Forum
- Vol. 39 (2) , 147-155
Neural Temporal Adaptive Sampling and Denoising
Despite recent advances in Monte Carlo path tracing at interactive rates, denoised image sequences generated with few samples per‐pixel often yield temporally unstable results and loss of high‐frequency details. We present a novel adaptive rendering method that increases temporal stability and image fidelity of low sample count path tracing by distributing samples via spatio‐temporal joint optimization of sampling and denoising. Adding temporal optimization to the sample predictor enables it to learn spatio‐temporal sampling strategies such as placing more samples in disoccluded regions, tracking specular highlights, etc; adding temporal feedback to the denoiser boosts the effective input sample count and increases temporal stability. The temporal approach also allows us to remove the initial uniform sampling step typically present in adaptive sampling algorithms. The sample predictor and denoiser are deep neural networks that we co‐train end‐to‐end over multiple consecutive frames. Our approach is scalable, allowing trade‐off between quality and performance, and runs at near real‐time rates while achieving significantly better image quality and temporal stability than previous methods.
- 1 May 2020
- Published by Wiley in Computer Graphics Forum
- Vol. 39 (2) , 147-155
Neural Temporal Adaptive Sampling and Denoising
Despite recent advances in Monte Carlo path tracing at interactive rates, denoised image sequences generated with few samples per‐pixel often yield temporally unstable results and loss of high‐frequency details. We present a novel adaptive rendering method that increases temporal stability and image fidelity of low sample count path tracing by distributing samples via spatio‐temporal joint optimization of sampling and denoising. Adding temporal optimization to the sample predictor enables it to learn spatio‐temporal sampling strategies such as placing more samples in disoccluded regions, tracking specular highlights, etc; adding temporal feedback to the denoiser boosts the effective input sample count and increases temporal stability. The temporal approach also allows us to remove the initial uniform sampling step typically present in adaptive sampling algorithms. The sample predictor and denoiser are deep neural networks that we co‐train end‐to‐end over multiple consecutive frames. Our approach is scalable, allowing trade‐off between quality and performance, and runs at near real‐time rates while achieving significantly better image quality and temporal stability than previous methods.