Optimizing Visual Quality and Efficiency for Immersive Graphics

You are cordially invited to attend the PhD Dissertation Defence of Luca Surace on Wednesday 21 May 2025 at 09:30 in room D1.13.

Abstract:
Advancements in graphics algorithms and display technologies are enabling more immersive and realistic virtual experiences, such as telepresence and digital replicas of the real world. However, achieving high visual fidelity comes with significant computational and power costs, which can sometimes hamper the adoption of the technology. In some situations, the quality of displayed content may exceed the limits of human vision, leading to a suboptimal use of computational resources. This highlights the need to optimize the trade-off between quality and efficiency in graphics applications. In this dissertation, I propose methods that leverage the limitations of the human visual system to optimize this trade-off. I first present a strategy to make the training of Generative Adversarial Networks (GANs) less sensitive to distortions that humans cannot detect while emphasizing perceptually important artifacts, enabling the reconstruction of visually significant image features. The strategy is evaluated using a newly trained objective metric and user experiments, demonstrating significant improvements in perceived image quality. Additionally, the results show higher sensitivity to distortions in images containing structures, such as edges and boundaries. This insight led us to develop another technique for handling geometry, specifically addressing distortions in mesh silhouettes, as they exhibit noticeable luminance discontinuities. The method computes the optimal Level Of Detail (LOD) of peripheral meshes to improve performance by reducing the polygon count. It also handles temporal changes between LODs, making it suitable for real-time applications. Besides computational efficiency, other factors affect power consumption of devices. In virtual reality headsets, the display is the main energy consumer, making power saving critical for battery-powered systems. To address this, I propose a method that leverages visual adaptation in immersive environments to optimize power efficiency by adjusting display brightness based on the content. All three techniques follow a common methodology: collecting perceptual data, modeling visual mechanisms, and validating through subjective experiments.

Dissertation Committee:
- Prof. Piotr Krzysztof Didyk, Università della Svizzera italiana, Switzerland (Research Advisor)
- Prof. Kai Hormann, Università della Svizzera italiana, Switzerland (Internal Member)
- Prof. Evanthia Papadopoulou, Università della Svizzera italiana, Switzerland (Internal Member)
- Prof. Qi Sun, New York University, US (External Member)
- Prof. Chris Wyman, NVIDIA Research, US (External Member)