Guardado en:
Detalles Bibliográficos
Autores principales: Pahari, Soham, Kumain, Sandeep C.
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2602.06419
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912884081033216
author Pahari, Soham
Kumain, Sandeep C.
author_facet Pahari, Soham
Kumain, Sandeep C.
contents Human visual attention on three-dimensional objects emerges from the interplay between bottom-up geometric processing and top-down semantic recognition. Existing 3D saliency methods rely on hand-crafted geometric features or learning-based approaches that lack semantic awareness, failing to explain why humans fixate on semantically meaningful but geometrically unremarkable regions. We introduce SemGeo-AttentionNet, a dual-stream architecture that explicitly formalizes this dichotomy through asymmetric cross-modal fusion, leveraging diffusion-based semantic priors from geometry-conditioned multi-view rendering and point cloud transformers for geometric processing. Cross-attention ensures geometric features query semantic content, enabling bottom-up distinctiveness to guide top-down retrieval. We extend our framework to temporal scanpath generation through reinforcement learning, introducing the first formulation respecting 3D mesh topology with inhibition-of-return dynamics. Evaluation on SAL3D, NUS3D and 3DVA datasets demonstrates substantial improvements, validating how cognitively motivated architectures effectively model human visual attention on three-dimensional surfaces.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06419
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Human Visual Attention on 3D Surfaces through Geometry-Queried Semantic Priors
Pahari, Soham
Kumain, Sandeep C.
Computer Vision and Pattern Recognition
Human visual attention on three-dimensional objects emerges from the interplay between bottom-up geometric processing and top-down semantic recognition. Existing 3D saliency methods rely on hand-crafted geometric features or learning-based approaches that lack semantic awareness, failing to explain why humans fixate on semantically meaningful but geometrically unremarkable regions. We introduce SemGeo-AttentionNet, a dual-stream architecture that explicitly formalizes this dichotomy through asymmetric cross-modal fusion, leveraging diffusion-based semantic priors from geometry-conditioned multi-view rendering and point cloud transformers for geometric processing. Cross-attention ensures geometric features query semantic content, enabling bottom-up distinctiveness to guide top-down retrieval. We extend our framework to temporal scanpath generation through reinforcement learning, introducing the first formulation respecting 3D mesh topology with inhibition-of-return dynamics. Evaluation on SAL3D, NUS3D and 3DVA datasets demonstrates substantial improvements, validating how cognitively motivated architectures effectively model human visual attention on three-dimensional surfaces.
title Learning Human Visual Attention on 3D Surfaces through Geometry-Queried Semantic Priors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.06419