GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chou, Zi-Ting, Huang, Sheng-Yu, Liu, I-Jieh, Wang, Yu-Chiang Frank
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913256268890112
author Chou, Zi-Ting
Huang, Sheng-Yu
Liu, I-Jieh
Wang, Yu-Chiang Frank
author_facet Chou, Zi-Ting
Huang, Sheng-Yu
Liu, I-Jieh
Wang, Yu-Chiang Frank
contents Utilizing multi-view inputs to synthesize novel-view images, Neural Radiance Fields (NeRF) have emerged as a popular research topic in 3D vision. In this work, we introduce a Generalizable Semantic Neural Radiance Field (GSNeRF), which uniquely takes image semantics into the synthesis process so that both novel view images and the associated semantic maps can be produced for unseen scenes. Our GSNeRF is composed of two stages: Semantic Geo-Reasoning and Depth-Guided Visual rendering. The former is able to observe multi-view image inputs to extract semantic and geometry features from a scene. Guided by the resulting image geometry information, the latter performs both image and semantic rendering with improved performances. Our experiments not only confirm that GSNeRF performs favorably against prior works on both novel-view image and semantic segmentation synthesis but the effectiveness of our sampling strategy for visual rendering is further verified.
format Preprint
id arxiv_https___arxiv_org_abs_2403_03608
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding
Chou, Zi-Ting
Huang, Sheng-Yu
Liu, I-Jieh
Wang, Yu-Chiang Frank
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Utilizing multi-view inputs to synthesize novel-view images, Neural Radiance Fields (NeRF) have emerged as a popular research topic in 3D vision. In this work, we introduce a Generalizable Semantic Neural Radiance Field (GSNeRF), which uniquely takes image semantics into the synthesis process so that both novel view images and the associated semantic maps can be produced for unseen scenes. Our GSNeRF is composed of two stages: Semantic Geo-Reasoning and Depth-Guided Visual rendering. The former is able to observe multi-view image inputs to extract semantic and geometry features from a scene. Guided by the resulting image geometry information, the latter performs both image and semantic rendering with improved performances. Our experiments not only confirm that GSNeRF performs favorably against prior works on both novel-view image and semantic segmentation synthesis but the effectiveness of our sampling strategy for visual rendering is further verified.
title GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2403.03608