TFCT-I2P: Three stream fusion network with color aware transformer for image-to-point cloud registration

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Peng, Muyao, An, Pei, Wan, Zichen, Yang, You, Liu, Qiong
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912053162147840
author Peng, Muyao
An, Pei
Wan, Zichen
Yang, You
Liu, Qiong
author_facet Peng, Muyao
An, Pei
Wan, Zichen
Yang, You
Liu, Qiong
contents Along with the advancements in artificial intelligence technologies, image-to-point-cloud registration (I2P) techniques have made significant strides. Nevertheless, the dimensional differences in the features of points cloud (three-dimension) and image (two-dimension) continue to pose considerable challenges to their development. The primary challenge resides in the inability to leverage the features of one modality to augment those of another, thereby complicating the alignment of features within the latent space. To address this challenge, we propose an image-to-point-cloud method named as TFCT-I2P. Initially, we introduce a Three-Stream Fusion Network (TFN), which integrates color information from images with structural information from point clouds, facilitating the alignment of features from both modalities. Subsequently, to effectively mitigate patch-level misalignments introduced by the inclusion of color information, we design a Color-Aware Transformer (CAT). Finally, we conduct extensive experiments on 7Scenes, RGB-D Scenes V2, ScanNet V2, and a self-collected dataset. The results demonstrate that TFCT-I2P surpasses state-of-the-art methods by 1.5% in Inlier Ratio, 0.4% in Feature Matching Recall, and 5.4% in Registration Recall. Therefore, we believe that the proposed TFCT-I2P contributes to the advancement of I2P registration.
format Preprint
id arxiv_https___arxiv_org_abs_2410_00360
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TFCT-I2P: Three stream fusion network with color aware transformer for image-to-point cloud registration
Peng, Muyao
An, Pei
Wan, Zichen
Yang, You
Liu, Qiong
Computer Vision and Pattern Recognition
Along with the advancements in artificial intelligence technologies, image-to-point-cloud registration (I2P) techniques have made significant strides. Nevertheless, the dimensional differences in the features of points cloud (three-dimension) and image (two-dimension) continue to pose considerable challenges to their development. The primary challenge resides in the inability to leverage the features of one modality to augment those of another, thereby complicating the alignment of features within the latent space. To address this challenge, we propose an image-to-point-cloud method named as TFCT-I2P. Initially, we introduce a Three-Stream Fusion Network (TFN), which integrates color information from images with structural information from point clouds, facilitating the alignment of features from both modalities. Subsequently, to effectively mitigate patch-level misalignments introduced by the inclusion of color information, we design a Color-Aware Transformer (CAT). Finally, we conduct extensive experiments on 7Scenes, RGB-D Scenes V2, ScanNet V2, and a self-collected dataset. The results demonstrate that TFCT-I2P surpasses state-of-the-art methods by 1.5% in Inlier Ratio, 0.4% in Feature Matching Recall, and 5.4% in Registration Recall. Therefore, we believe that the proposed TFCT-I2P contributes to the advancement of I2P registration.
title TFCT-I2P: Three stream fusion network with color aware transformer for image-to-point cloud registration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.00360