Výsledky vyhledávání

Report

NeB-SLAM: Neural Blocks-based Salable RGB-D SLAM for Unknown Scenes

Autor: Bai, Lizhi, Tian, Chunqi, Yang, Jun, Zhang, Siyu, Liang, Weijian

Neural implicit representations have recently demonstrated considerable potential in the field of visual simultaneous localization and mapping (SLAM). This is due to their inherent advantages, including low storage overhead and representation continu

Externí odkaz: http://arxiv.org/abs/2405.15151

Zobrazit plný text záznamu

Report

Superpixel Semantics Representation and Pre-training for Vision-Language Task

Autor: Zhang, Siyu, Chen, Yeming, Sun, Yaoru, Wang, Fang, Yang, Jun, Bai, Lizhi, Gao, Shangce

The key to integrating visual language tasks is to establish a good alignment strategy. Recently, visual semantic representation has achieved fine-grained visual understanding by dividing grids or image patches. However, the coarse-grained semantic i

Externí odkaz: http://arxiv.org/abs/2310.13447

Zobrazit plný text záznamu

Report

Pixel Difference Convolutional Network for RGB-D Semantic Segmentation

Autor: Yang, Jun, Bai, Lizhi, Sun, Yaoru, Tian, Chunqi, Mao, Maoyu, Wang, Guorun

RGB-D semantic segmentation can be advanced with convolutional neural networks due to the availability of Depth data. Although objects cannot be easily discriminated by just the 2D appearance, with the local pixel difference and geometric patterns in

Externí odkaz: http://arxiv.org/abs/2302.11951

Zobrazit plný text záznamu

Report

DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation

Autor: Bai, Lizhi, Yang, Jun, Tian, Chunqi, Sun, Yaoru, Mao, Maoyu, Xu, Yanjun, Xu, Weirong

Combining RGB images and the corresponding depth maps in semantic segmentation proves the effectiveness in the past few years. Existing RGB-D modal fusion methods either lack the non-linear feature fusion ability or treat both modal images equally, r

Externí odkaz: http://arxiv.org/abs/2210.06747

Zobrazit plný text záznamu