# Monocular depth estimation

Distill-Any-Depth is a new SOTA monocular depth estimation model trained using knowledge distillation algorithms.

DepthMaster is a refined single-step diffusion model that customizes generative features from diffusion models for discriminative depth estimation tasks.

DepthPro is a monocular depth estimation model capable of predicting depth from a single image.

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, offering finer details and stronger robustness.

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on a large amount of synthetic and real images, providing fine depth details and high robustness.

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on large-scale synthetic and real images. Compared to V1, it captures finer details and is more robust.

Depth Anything is a depth estimation model based on the DPT architecture and DINOv2 backbone network, trained on approximately 62 million images, achieving state-of-the-art results in relative and absolute depth estimation tasks.

ZoeDepth is a depth estimation model fine-tuned on NYU and KITTI datasets, capable of estimating depth values in actual metric units.

ZoeDepth is a model for monocular depth estimation, specifically fine-tuned on the NYU dataset, capable of zero-shot transfer and metric depth estimation.

A depth estimation model based on Transformers.js, adapted for ONNX weights version, used to predict depth information from images.

Small ONNX-format depth estimation model adapted for Transformers.js framework, suitable for web-based depth map prediction

Depth Anything is a powerful depth estimation model that unleashes the potential of depth estimation using large-scale unlabeled data.

Depth Anything is a depth estimation model that leverages large-scale unlabeled data to enhance performance, suitable for monocular depth estimation tasks.

Converted MiDaS model to ONNX format for monocular depth estimation in Unity Sentis

DPT model based on SwinV2 backbone network for monocular depth estimation, trained on 1.4 million images

DPT model based on SwinV2 backbone network for monocular depth estimation, trained on 1.4 million images.

The DPT (Dense Prediction Transformer) model is trained on 1.4 million images for monocular depth estimation. This model uses Swinv2 as the backbone network and is suitable for high-precision depth prediction tasks.

Monocular depth estimation model based on BEiT backbone network, capable of inferring detailed depth information from a single image

A monocular depth estimation model based on Vision Transformer (ViT), trained on 1.4 million images

The GLPN model is trained on the NYUv2 dataset for monocular depth estimation, combining global and local path networks to achieve high-precision depth prediction.

GLPN is a model for monocular depth estimation, using SegFormer as the backbone network with a lightweight head added on top for depth prediction.