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

3D semantic instance results



Infoavg ap 25%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
0.7641.0000.8970.8370.7530.8300.4590.8240.6990.6290.6530.4380.6501.0000.8800.8580.6901.0000.650