Robust Mesh Saliency Ground Truth Acquisition in VR via View Cone Sampling and Manifold Diffusion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910111487754240 |
|---|---|
| author | Zheng, Guoquan Hao, Jie Duan, Huiyu Tang, Long Yang, Shuo Zhu, Yucheng Han, Yongming Yuan, Liang Callet, Patrick Le Zhai, Guangtao |
| author_facet | Zheng, Guoquan Hao, Jie Duan, Huiyu Tang, Long Yang, Shuo Zhu, Yucheng Han, Yongming Yuan, Liang Callet, Patrick Le Zhai, Guangtao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_02721 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Robust Mesh Saliency Ground Truth Acquisition in VR via View Cone Sampling and Manifold Diffusion Zheng, Guoquan Hao, Jie Duan, Huiyu Tang, Long Yang, Shuo Zhu, Yucheng Han, Yongming Yuan, Liang Callet, Patrick Le Zhai, Guangtao Computer Vision and Pattern Recognition Multimedia 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. |
| title | Robust Mesh Saliency Ground Truth Acquisition in VR via View Cone Sampling and Manifold Diffusion |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2601.02721 |