Alexandr Kuznetsov
Alexandr Kuznetsov has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Anton Kaplanyan
Intel Corporation, Bellevue, Washington, USA
2 shared publications - Harish Anand
Advanced Micro Devices, Inc
2 shared publications - Rama Harihara
Advanced Micro Devices (AMD), San Jose, USA
2 shared publications - Stavros Diolatzis
Intel Corporation, Nice, France
2 shared publications - Sungye Kim
Advanced Micro Devices, Inc
2 shared publications - Wojciech Kaliński
Advanced Micro Devices, Inc
2 shared publications
Latest Publications
- 10 September 2026
- Published by Springer Nature
- p. 205-224
Temporally Stable Generative Illumination with a One-Step Diffusion Model
- 10 September 2026
- Published by Springer Nature
- p. 205-224
Temporally Stable Generative Illumination with a One-Step Diffusion Model
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Lightweight Attention-based Indirect Illumination
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessLightweight Attention-based Indirect Illumination
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Image-GS: Content-Adaptive Image Representation via 2D Gaussians
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessImage-GS: Content-Adaptive Image Representation via 2D Gaussians
- Open Access
- 13 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
N-Dimensional Gaussians for Fitting of High Dimensional Functions
In the wake of many new ML-inspired approaches for reconstructing and representing high-quality 3D content, recent hybrid and explicitly learned representations exhibit promising performance and quality characteristics. However, their scaling to higher dimensions is challenging, e.g. when accounting for dynamic content with respect to additional parameters such as material properties, illumination, or time. In this paper, we tackle these challenges for an explicit representations based on Gaussian mixture models. With our solutions, we arrive at efficient fitting of compact N-dimensional Gaussian mixtures and enable efficient evaluation at render time: For fast fitting and evaluation, we introduce a high-dimensional culling scheme that efficiently bounds N-D Gaussians, inspired by Locality Sensitive Hashing. For adaptive refinement yet compact representation, we introduce a loss-adaptive density control scheme that incrementally guides the use of additional capacity towards missing details. With these tools we can for the first time represent complex appearance that depends on many input dimensions beyond position or viewing angle within a compact, explicit representation optimized in minutes and rendered in milliseconds.
- 13 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessN-Dimensional Gaussians for Fitting of High Dimensional Functions
In the wake of many new ML-inspired approaches for reconstructing and representing high-quality 3D content, recent hybrid and explicitly learned representations exhibit promising performance and quality characteristics. However, their scaling to higher dimensions is challenging, e.g. when accounting for dynamic content with respect to additional parameters such as material properties, illumination, or time. In this paper, we tackle these challenges for an explicit representations based on Gaussian mixture models. With our solutions, we arrive at efficient fitting of compact N-dimensional Gaussian mixtures and enable efficient evaluation at render time: For fast fitting and evaluation, we introduce a high-dimensional culling scheme that efficiently bounds N-D Gaussians, inspired by Locality Sensitive Hashing. For adaptive refinement yet compact representation, we introduce a loss-adaptive density control scheme that incrementally guides the use of additional capacity towards missing details. With these tools we can for the first time represent complex appearance that depends on many input dimensions beyond position or viewing angle within a compact, explicit representation optimized in minutes and rendered in milliseconds.