Submitted by Huayao Liu.

Submission data

Full nameUsing dual decoder U-Net and Point Grouping
Publication titleHIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor
Publication authorsH. Liu, R. Liu, K. Yang, J. Zhang, K. Peng, R. Stiefelhagen
Publication venueICCVW 2021
Publication URLhttps://arxiv.org/abs/2107.03180
Input Data TypesUses Color,Uses Geometry        Uses 3D
Programming language(s)Python with Cuda
HardwareRTX 3090
Submission creation date5 Jul, 2021
Last edited12 Aug, 2021
Last uploaded3 Aug, 2021

3D semantic instance results



Infoavg apbathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
0.4360.6300.5080.4800.3100.6240.0650.6380.1740.2560.3840.1940.4280.7590.2890.5740.4000.8490.291