Edoardo Alberto Dominici
Research Subjects
Edoardo Alberto Dominici has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Markus Steinberger
Graz University of Technology
4 shared publications - Arno Coomans
Huawei Technologies Switzerland
3 shared publications - Christian Döring
Huawei Technologies Germany
3 shared publications - Giacomo Nazzaro
Huawei Technologies
3 shared publications - Konstantinos Vardis
Department of Informatics, Athens University of Economics and Business, Athens, Greece
3 shared publications - Floor Verhoeven
ETH Zurich, Switzerland
2 shared publications
Latest Publications
- Open Access
- 1 May 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Computer Graphics and Interactive Techniques
- Vol. 9 (1) , 1-19
PixelSync: Enhancing Texture Generation via Explicit Feature Synchronization
The generation of consistent multi-view images is essential for diffusion-based 3D texture synthesis, a key component of modern 3D content pipelines. However, existing methods remain weakly coupled across viewpoints, often exhibiting inconsistencies between views that result in artifacts such as ghosting, misalignment, and texture distortions. We introduce PixelSync, a training-free mechanism that explicitly enforces multi-view consistency during the diffusion process. Our method operates in two stages. First, we compute visibility-aware pixel correspondences between known views in a fast pre-computation step by utilizing geometric information obtained from a given 3D model. Then, during the diffusion process, we enforce consistency through two complementary algorithms: (i) attention synchronization, by modifying the attention scores in the U-Net’s down- and mid-blocks, and (ii) latent synchronization, by progressively aligning features on their corresponding shared pixels. PixelSync can be seamlessly integrated into pre-trained diffusion models without retraining, offering a lightweight and effective solution. We demonstrate the effectiveness of our approach for generative texture synthesis by plugging PixelSync into established multi-view diffusion backbones, showcasing reduced cross-view artifacts and improved global coherence across standard quantitative and qualitative evaluations.
- 1 May 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Computer Graphics and Interactive Techniques
- Vol. 9 (1) , 1-19
Open AccessPixelSync: Enhancing Texture Generation via Explicit Feature Synchronization
The generation of consistent multi-view images is essential for diffusion-based 3D texture synthesis, a key component of modern 3D content pipelines. However, existing methods remain weakly coupled across viewpoints, often exhibiting inconsistencies between views that result in artifacts such as ghosting, misalignment, and texture distortions. We introduce PixelSync, a training-free mechanism that explicitly enforces multi-view consistency during the diffusion process. Our method operates in two stages. First, we compute visibility-aware pixel correspondences between known views in a fast pre-computation step by utilizing geometric information obtained from a given 3D model. Then, during the diffusion process, we enforce consistency through two complementary algorithms: (i) attention synchronization, by modifying the attention scores in the U-Net’s down- and mid-blocks, and (ii) latent synchronization, by progressively aligning features on their corresponding shared pixels. PixelSync can be seamlessly integrated into pre-trained diffusion models without retraining, offering a lightweight and effective solution. We demonstrate the effectiveness of our approach for generative texture synthesis by plugging PixelSync into established multi-view diffusion backbones, showcasing reduced cross-view artifacts and improved global coherence across standard quantitative and qualitative evaluations.
- 15 April 2026
- Published by Wiley in Computer Graphics Forum
Real‐time Rendering with a Neural Irradiance Volume
Rendering diffuse global illumination in real‐time is often approximated by pre‐computing and storing irradiance in a 3D grid of probes. As long as most of the scene remains static, probes approximate irradiance for all surfaces immersed in the irradiance volume, including novel dynamic objects. This approach, however, suffers from aliasing artifacts and high memory consumption. We propose Neural Irradiance Volume (NIV), a neural‐based technique that allows accurate real‐time rendering of diffuse global illumination via a compact pre‐computed model, overcoming the limitations of traditional probe‐based methods, such as the expensive memory footprint, aliasing artifacts, and scene‐specific heuristics. The key insight is that neural compression creates an adaptive and amortized representation of irradiance, circumventing the cubic scaling of grid‐based methods. Our superior memory‐scaling improves quality by at least 10x at the same memory budget, and enables a straightforward representation of higher‐dimensional irradiance fields, allowing rendering of time‐varying or dynamic effects without requiring additional computation at runtime. Unlike other neural rendering techniques, our method works within strict realtime constraints, providing fast inference (around 1 ms per frame on consumer GPUs at full HD resolution), reduced memory usage (1–5 MB for medium‐sized scenes), and only requires a G‐buffer as input, without expensive ray tracing or denoising.
- 15 April 2026
- Published by Wiley in Computer Graphics Forum
Real‐time Rendering with a Neural Irradiance Volume
Rendering diffuse global illumination in real‐time is often approximated by pre‐computing and storing irradiance in a 3D grid of probes. As long as most of the scene remains static, probes approximate irradiance for all surfaces immersed in the irradiance volume, including novel dynamic objects. This approach, however, suffers from aliasing artifacts and high memory consumption. We propose Neural Irradiance Volume (NIV), a neural‐based technique that allows accurate real‐time rendering of diffuse global illumination via a compact pre‐computed model, overcoming the limitations of traditional probe‐based methods, such as the expensive memory footprint, aliasing artifacts, and scene‐specific heuristics. The key insight is that neural compression creates an adaptive and amortized representation of irradiance, circumventing the cubic scaling of grid‐based methods. Our superior memory‐scaling improves quality by at least 10x at the same memory budget, and enables a straightforward representation of higher‐dimensional irradiance fields, allowing rendering of time‐varying or dynamic effects without requiring additional computation at runtime. Unlike other neural rendering techniques, our method works within strict realtime constraints, providing fast inference (around 1 ms per frame on consumer GPUs at full HD resolution), reduced memory usage (1–5 MB for medium‐sized scenes), and only requires a G‐buffer as input, without expensive ray tracing or denoising.
- Open Access
Real-time Rendering with a Neural Irradiance Volume
Rendering diffuse global illumination in real-time is often approximated by pre-computing and storing irradiance in a 3D grid of probes. As long as most of the scene remains static, probes approximate irradiance for all surfaces immersed in the irradiance volume, including novel dynamic objects. This approach, however, suffers from aliasing artifacts and high memory consumption. We propose Neural Irradiance Volume (NIV), a neural-based technique that allows accurate real-time rendering of diffuse global illumination via a compact pre-computed model, overcoming the limitations of traditional probe-based methods, such as the expensive memory footprint, aliasing artifacts, and scene-specific heuristics. The key insight is that neural compression creates an adaptive and amortized representation of irradiance, circumventing the cubic scaling of grid-based methods. Our superior memory-scaling improves quality by at least 10x at the same memory budget, and enables a straightforward representation of higher-dimensional irradiance fields, allowing rendering of time-varying or dynamic effects without requiring additional computation at runtime. Unlike other neural rendering techniques, our method works within strict real-time constraints, providing fast inference (around 1 ms per frame on consumer GPUs at full HD resolution), reduced memory usage (1-5 MB for medium-sized scenes), and only requires a G-buffer as input, without expensive ray tracing or denoising.
Open AccessReal-time Rendering with a Neural Irradiance Volume
Rendering diffuse global illumination in real-time is often approximated by pre-computing and storing irradiance in a 3D grid of probes. As long as most of the scene remains static, probes approximate irradiance for all surfaces immersed in the irradiance volume, including novel dynamic objects. This approach, however, suffers from aliasing artifacts and high memory consumption. We propose Neural Irradiance Volume (NIV), a neural-based technique that allows accurate real-time rendering of diffuse global illumination via a compact pre-computed model, overcoming the limitations of traditional probe-based methods, such as the expensive memory footprint, aliasing artifacts, and scene-specific heuristics. The key insight is that neural compression creates an adaptive and amortized representation of irradiance, circumventing the cubic scaling of grid-based methods. Our superior memory-scaling improves quality by at least 10x at the same memory budget, and enables a straightforward representation of higher-dimensional irradiance fields, allowing rendering of time-varying or dynamic effects without requiring additional computation at runtime. Unlike other neural rendering techniques, our method works within strict real-time constraints, providing fast inference (around 1 ms per frame on consumer GPUs at full HD resolution), reduced memory usage (1-5 MB for medium-sized scenes), and only requires a G-buffer as input, without expensive ray tracing or denoising.
- 23 April 2024
- Published by Wiley in Computer Graphics Forum
- Vol. 43 (2)
Real‐time Neural Rendering of Dynamic Light Fields
Synthesising high‐quality views of dynamic scenes via path tracing is prohibitively expensive. Although caching offline‐quality global illumination in neural networks alleviates this issue, existing neural view synthesis methods are limited to mainly static scenes, have low inference performance or do not integrate well with existing rendering paradigms. We propose a novel neural method that is able to capture a dynamic light field, renders at real‐time frame rates at 1920×1080 resolution and integrates seamlessly with Monte Carlo ray tracing frameworks. We demonstrate how a combination of spatial, temporal and a novel surface‐space encoding are each effective at capturing different kinds of spatio‐temporal signals. Together with a compact fully‐fused neural network and architectural improvements, we achieve a twenty‐fold increase in network inference speed compared to related methods at equal or better quality. Our approach is suitable for providing offline‐quality real‐time rendering in a variety of scenarios, such as free‐viewpoint video, interactive multi‐view rendering, or streaming rendering. Finally, our work can be integrated into other rendering paradigms, e.g., providing a dynamic background for interactive scenarios where the foreground is rendered with traditional methods.
- 23 April 2024
- Published by Wiley in Computer Graphics Forum
- Vol. 43 (2)
Real‐time Neural Rendering of Dynamic Light Fields
Synthesising high‐quality views of dynamic scenes via path tracing is prohibitively expensive. Although caching offline‐quality global illumination in neural networks alleviates this issue, existing neural view synthesis methods are limited to mainly static scenes, have low inference performance or do not integrate well with existing rendering paradigms. We propose a novel neural method that is able to capture a dynamic light field, renders at real‐time frame rates at 1920×1080 resolution and integrates seamlessly with Monte Carlo ray tracing frameworks. We demonstrate how a combination of spatial, temporal and a novel surface‐space encoding are each effective at capturing different kinds of spatio‐temporal signals. Together with a compact fully‐fused neural network and architectural improvements, we achieve a twenty‐fold increase in network inference speed compared to related methods at equal or better quality. Our approach is suitable for providing offline‐quality real‐time rendering in a variety of scenarios, such as free‐viewpoint video, interactive multi‐view rendering, or streaming rendering. Finally, our work can be integrated into other rendering paradigms, e.g., providing a dynamic background for interactive scenarios where the foreground is rendered with traditional methods.
- Open Access
- 28 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Focus Range: Production Ray Tracing of Depth of Field
Defocus blur adds realism to computer generated images by modelling the restricted focus range of physical camera lenses. It allows artists to draw the viewer’s attention to in-focus regions of the image by separating them from the background. The widely used thin lens model provides a simple approach to achieve this effect, allowing artists to control the frame’s appearance through the distance to the focus plane and the aperture size. Our proposed focus range model extends the focus distance to a range. This allows artists to keep characters fully in focus and independently define the out-of-focus blur. We demonstrate how to achieve this robustly in the presence of specular BSDFs, ray-oriented geometry and multiple light bounces. Additionally, we share our practical experience of integrating this model into our production renderer Glimpse.
- 28 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessFocus Range: Production Ray Tracing of Depth of Field
Defocus blur adds realism to computer generated images by modelling the restricted focus range of physical camera lenses. It allows artists to draw the viewer’s attention to in-focus regions of the image by separating them from the background. The widely used thin lens model provides a simple approach to achieve this effect, allowing artists to control the frame’s appearance through the distance to the focus plane and the aperture size. Our proposed focus range model extends the focus distance to a range. This allows artists to keep characters fully in focus and independently define the out-of-focus blur. We demonstrate how to achieve this robustly in the presence of specular BSDFs, ray-oriented geometry and multiple light bounces. Additionally, we share our practical experience of integrating this model into our production renderer Glimpse.