PardisTaghavi/SwinMTL
[IROS24]A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images
This project helps roboticists and autonomous vehicle developers process single camera images to understand both how far away objects are and what those objects are (e.g., road, car, pedestrian). You input a standard monocular camera image, and it outputs two enhanced images: one showing depth perception and another with objects clearly segmented and labeled. This is ideal for those building navigation systems or perception stacks for robots.
No commits in the last 6 months.
Use this if you need to rapidly extract both depth information and semantic understanding from a single camera feed for robotic navigation or environmental perception.
Not ideal if your application requires extremely high-precision depth sensing that might be better suited for stereo cameras, LiDAR, or other dedicated depth sensors.
Stars
48
Forks
4
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Mar 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/PardisTaghavi/SwinMTL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vita-epfl/monoloco
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social...
fangchangma/self-supervised-depth-completion
ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and...
nburrus/stereodemo
Small Python utility to compare and visualize the output of various stereo depth estimation algorithms
JiawangBian/sc_depth_pl
SC-Depth (V1, V2, and V3) for Unsupervised Monocular Depth Estimation ...
wvangansbeke/Sparse-Depth-Completion
Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st...