Benchmark (up-to-date)

Public Benchmark

Disclaimer:

  • This is just a benchmark on some standard datasets, which means the model does not necessarily become the actual “SOTA” for in-the-wild applications
  • This benchmark focuses on accuracy metrics but no latency metrics, which are also an essential part of the real-time applications

Papers with Code - Monocular Depth Estimation

Personal Benchmark

Personal benchmark


Personal Notes

From depth estimation to Pseudo-LIDAR

Augmentation techniques for depth model


Prominent Works

These works may not be “SOTA” on some specific datasets but have a high potential for real-world, in-the-wild applications

Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera (2025)

Depth Any Camera

Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation (2024)

https://promptda.github.io/

Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction (2024)

Lotus

World-consistent Video Diffusion with Explicit 3D Modeling (2024)

WVD

RollingDepth: Video Depth without Video Models (2024)

https://github.com/prs-eth/rollingdepth

Depth Anything - CVPR 2024

https://github.com/DepthAnything/Depth-Anything-V2

https://github.com/LiheYoung/Depth-Anything

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos (2024)

https://github.com/Tencent/DepthCrafter

Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation - Neurips 2024

https://github.com/albert100121/Depth-Anywhere

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (2024)

https://github.com/apple/ml-depth-pro

https://github.com/apple/ml-depth-pro/issues/1

UniDepth: Universal Monocular Metric Depth Estimation - CVPR 2024

https://github.com/lpiccinelli-eth/UniDepth

Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation - CVPR 2024

https://github.com/prs-eth/marigold

Booster: A Benchmark for Depth from Images of Specular and Transparent Surfaces (2023)

arxiv.org

Deep Depth from Focus with Differential Focus Volume - CVPR 2022

arxiv.org

https://github.com/fuy34/DFV

Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer (2020)

https://github.com/isl-org/MiDaS


Datasets & Simulator

RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos

https://github.com/wildrgbd/wildrgbd

CARLA Simulator

https://github.com/carla-simulator/carla


Other References