Robust Mesh Saliency Ground Truth Acquisition in VR via View Cone Sampling and Manifold Diffusion

TL;DR

This paper introduces a novel framework combining view cone sampling and manifold diffusion to improve 3D mesh saliency ground truth acquisition in VR, addressing existing sampling and propagation limitations.

Contribution

It proposes a view cone sampling strategy and a hybrid manifold-Euclidean diffusion algorithm to enhance saliency accuracy on complex 3D topologies in VR.

Findings

Improved sampling robustness with view cone sampling.

Enhanced topologically-consistent saliency propagation.

Better alignment with human visual perception in VR.

Abstract

As the complexity of 3D digital content grows exponentially, understanding human visual attention is critical for optimizing rendering and processing resources. Therefore, reliable 3D mesh saliency ground truth (GT) is essential for human-centric visual modeling in virtual reality (VR). However, existing VR eye-tracking frameworks are fundamentally bottlenecked by their underlying acquisition and generation mechanisms. The reliance on zero-area single ray sampling (SRS) fails to capture contextual features, leading to severe texture aliasing and discontinuous saliency signals. And the conventional application of Euclidean smoothing propagates saliency across disconnected physical gaps, resulting in semantic confusion on complex 3D manifolds. This paper proposes a robust framework to address these limitations. We first introduce a view cone sampling (VCS) strategy, which simulates the human foveal receptive field via Gaussian-distributed ray bundles to improve sampling robustness for complex topologies. Furthermore, a hybrid Manifold-Euclidean constrained diffusion (HCD) algorithm is developed, fusing manifold geodesic constraints with Euclidean scales to ensure topologically-consistent saliency propagation. We demonstrate the improvement in performance over baseline methods and the benefits for downstream tasks through subjective experiments and qualitative and quantitative methods. By mitigating "topological short-circuits" and aliasing, our framework provides a high-fidelity 3D attention acquisition paradigm that aligns with natural human perception, offering a more accurate and robust baseline for 3D mesh saliency research.