D

Dpt Beit Large 384

Developed by Intel
Monocular depth estimation model based on BEiT backbone network, capable of inferring detailed depth information from a single image
Downloads 135
Release Time : 11/28/2023

Model Overview

This DPT model uses BEiT as backbone network with added neck and head structures for monocular depth estimation. Mainly used for inferring detailed depth information from single images or single viewpoints.

Model Features

BEiT backbone network
Uses BEiT Transformer as backbone network to achieve highest quality depth estimation
Zero-shot transfer
Supports zero-shot depth estimation without fine-tuning for specific scenes
Multi-resolution support
Provides multiple training resolution versions including 384x384 and 512x512

Model Capabilities

Monocular depth estimation
Image depth map generation
Zero-shot transfer learning

Use Cases

Computer vision
3D reconstruction
Generate depth information from single images for 3D scene reconstruction
Autonomous driving
Provide environmental depth perception for autonomous driving systems
Augmented reality
Provide scene depth information for AR applications
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase