The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
-
Updated
Mar 13, 2025 - Python
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
🌊 Images to → 3D Parallax effect video. A free and open source ImmersityAI alternative
[CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth
[CVPR 2025] DEFOM-Stereo: Depth foundation model based stereo matching
CVPR 2020 - On the uncertainty of self-supervised monocular depth estimation
[WACV 2023] Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem
Semi-supervised monocular depth map prediction
Monocular depth prediction with PyTorch
Official implementation of the paper "Maximizing Self-supervision from Thermal Image for Effective Self-supervised Learning of Depth and Ego-motion"
Inferring distributions over depth from a single image, IROS 2019
Re-implementation: "[CVPR 2017] Learning Detailed Face Reconstruction from a Single Image".
[WACV2023] Frequency Aware Self-supervised Depth Estimation
Official implementation of "LocalBins: Improving Depth Estimation by Learning Local Distributions"
PatchGAN's for refining Monocular Depth Estimation.
Code for "Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce Model" as published at CVPR 2021.
The implementations for SLURP: Side Learning Uncertainty for Regression Problems (BMVC 2021)
The official code for ICRA 2021 Paper: "Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation"
Supplement materials for Micro Quadcopter Obstacle Avoidance with a Lightweight Monocular Depth Network
Replicated results from DenseDepth using DenseNet169 in Python.
High-performance TensorRT (C++/CUDA) inference for UniDepth V2 — metric depth + confidence/uncertainty + point cloud, optimized with FP16 and CUDA Graph (RTX 5070 benchmarks).
Add a description, image, and links to the monocular-depth topic page so that developers can more easily learn about it.
To associate your repository with the monocular-depth topic, visit your repo's landing page and select "manage topics."