AI RESEARCH
Robust Mesh Saliency Ground Truth Acquisition in VR via View Cone Sampling and Manifold Diffusion
arXiv CS.CV
•
ArXi:2601.02721v2 Announce Type: replace 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.