twhui/RM-Depth
RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes, CVPR 2022
This project helps self-driving car engineers, robotics developers, and drone operators understand their environment more deeply by extracting crucial 3D information from standard video. It takes a single video frame as input and outputs a detailed depth map, showing how far away objects are, along with the precise movement of both the camera and any moving objects in the scene. This is particularly useful for systems navigating complex, dynamic real-world settings.
No commits in the last 6 months.
Use this if you need to quickly and accurately generate depth maps and track object motion from standard video feeds without relying on specialized hardware or pre-labeled data.
Not ideal if your application requires a strictly static scene or if you already have access to specialized depth sensors like LiDAR.
Stars
41
Forks
—
Language
—
License
—
Category
Last pushed
Oct 04, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/twhui/RM-Depth"
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...