G

Glpn Kitti

Developed by vinvino02
GLPN is a model for monocular depth estimation, using SegFormer as the backbone network with a lightweight head added on top for depth prediction.
Downloads 3,401
Release Time : 3/2/2022

Model Overview

Global-Local Path Network (GLPN) is a monocular depth estimation model trained on the KITTI dataset, suitable for predicting depth information from a single image.

Model Features

Global-Local Path Network
Combines global and local information for depth estimation to improve prediction accuracy.
Lightweight head design
Adds a lightweight head on the SegFormer backbone to maintain efficient inference speed.
Fine-tuned on KITTI dataset
Specifically fine-tuned on the KITTI dataset, suitable for depth estimation in scenarios like autonomous driving.

Model Capabilities

Monocular depth estimation
Image depth prediction
3D scene understanding

Use Cases

Autonomous driving
Road scene depth estimation
Used for depth perception of road environments in autonomous driving systems.
Computer vision
3D scene reconstruction
Generates depth maps from single images to assist in 3D scene reconstruction.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase