Sbrunoberenguel/FreDSNet
Code to test FreDSNet: Frequential Depth estimation and Semantic segmentation Network
This project helps operations engineers, architects, or facility managers analyze indoor environments from single panoramic images. It takes an equirectangular panorama of a room or space and outputs a map showing the distance of objects from the camera (depth) and identifies different objects or regions within the panorama (semantic segmentation). Additionally, it can generate a basic 3D reconstruction of the environment.
No commits in the last 6 months.
Use this if you need to quickly understand the layout and contents of an indoor space from a single 360-degree image, without complex 3D scanning equipment.
Not ideal if you require highly precise, production-grade 3D models or if you are working with non-panoramic images.
Stars
44
Forks
5
Language
Python
License
GPL-3.0
Category
Last pushed
Oct 26, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Sbrunoberenguel/FreDSNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
JonasSchult/Mask3D
Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet,...
nsavinov/semantic3dnet
Point cloud semantic segmentation via Deep 3D Convolutional Neural Network
PRBonn/LiDAR-MOS
(LMNet) Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting...
yanx27/2DPASS
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds (ECCV 2022) :fire:
ctu-vras/traversability_estimation
Semantic Segmentation of Images and Point Clouds for Traversability Estimation