A list of recent monocular depth estimation work, inspired by awesome-computer-vision.
The list is mainly focusing on recent work after 2020
High Performance
- Metric3D v2 A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation (high-performing metric depth on zero-shot evaluation), arxiv 2024 | github
- UniDepth: Universal Monocular Metric Depth Estimation, (universal metric depth estimation; one's zero-shot performance match depth-anything on NYUv2), CVPR 2024 | github
- Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation (diffusion), CVPR 2024 | github
- ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation (diffusion), CVPR 2024 | github
- Harnessing Diffusion Models for Visual Perception with Meta Prompts (diffusion), arxiv 2024 | github
- DepthFM: Fast Monocular Depth Estimation with Flow Matching, (Depth Estimation using Flow Matching), arXiv 2024
- Unleashing the Power of Large-Scale Unlabeled Data, CVPR 2024 | github huggingface
- EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment (Diffusion), arXiv 2023 | github
- Harnessing Diffusion Models for Visual Perception with Meta Prompts, arXiv 2023 | github
- IEBins: Iterative Elastic Bins for Monocular Depth Estimation, NeurIPS 2023 | github
- Text-Image Alignment for Diffusion-Based Perception (Diffusion), CVPR 2024 | github
- Robust Monocular Depth Estimation under Challenging Conditions, ICCV 2023 | github
- Unleashing Text-to-Image Diffusion Models for Visual Perception (Diffusion), ICCV 2023 | github
- Neural Video Depth Stabilizer , ICCV 2023 | github
- The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation (Diffusion), arXiv 2023
- All in Tokens: Unifying Output Space of Visual Tasks via Soft Token (tokenized), arXiv 2023 | github
- Revealing the Dark Secrets of Masked Image Modeling (tokenization approach), CVPR 2023 | github
- Internal Discretization for Monocular Depth Estimation (tokenization approach), CVPR 2023 | github
- Neural Video Depth Stabilizer, ICCV 2023 | github
- VA-DepthNet: A Variational Approach to Single Image Depth Prediction, ICLR 2023 | github
- Improving Deep Regression with Ordinal Entropy, ICLR 2023 | github
- DDP: Diffusion Model for Dense Visual Prediction (Diffusion), arXiv 2023 | github
- PixelFormer: Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention (Diffusion), WACV 2023 | github
- LocalBins: Improving Depth Estimation by Learning Local Distributions, CVPR 2022 | github
- NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation, CVPR 2022 | github
Self-Supervised Depth Estimation
- SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimation, AAAI 2024
- Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Models, arxiv 2024
- Complete contextual information extraction for self-supervised monocular depth estimation, CVIU 2024
- FA-Depth: Toward Fast and Accurate Self-supervised Monocular Depth Estimation, arxiv 2024
- Two-in-One Depth: Bridging the Gap Between Monocular and Binocular Self-Supervised Depth Estimation, ICCV 2023
- DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium, CVPR 2023
- Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem, WACV 2023
- 3D Distillation: Improving Self-Supervised Monocular Depth Estimation on Reflective Surfaces, ICCV 2023
- GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes, ICCV 2023
- CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision, ICCV 2023
- Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation, ICCV 2023 | github
- Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation, AAAI 2023
- Self-supervised monocular depth estimation with a vision transformer, 3DV 2022 | github
- Self-Supervised Surround-View Depth Estimation with Volumetric Feature Fusion, NeurIPS 2022
- Devnet: Self-supervised monocular depth learning via density volume construction, ECCV 2022 | github
- Exploiting Pseudo Labels in a Self-Supervised Learning Framework for Improved Monocular Depth Estimation, ECCV 2022
- RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation, ECCV 2022 | github
- Toward Practical Monocular Indoor Depth Estimation, CVPR 2022 | github
- Multi-Frame Self-Supervised Depth with Transformers, CVPR 2022
Metric Depth from Single Image
- Unleashing the Power of Large-Scale Unlabeled Data, CVPR 2024 | github huggingface
- Metric3D v2 A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation (high-performing metric depth on zero-shot evaluation), arxiv 2024 | github
- UniDepth: Universal Monocular Metric Depth Estimation, (universal metric depth estimation; one's zero-shot performance match depth-anything on NYUv2), CVPR 2024 | github
- ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth, arXiv 2023 | github
- Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image, ICCV 2023 | github
- Towards Zero-Shot Scale-Aware Monocular Depth Estimation, ICCV 2023
- Toward Practical Monocular Indoor Depth Estimation, CVPR 2022 | github
Depth for Non-Lambertain Surface
Depth from Dual-Pixel, optics, or photography
- Shakes on a Plane: Unsupervised Depth Estimation from Unstabilized Photography, CVPR 2023 | github
- Fully Self-Supervised Depth Estimation from Defocus Clue, CVPR 2023 | github
- Calibration-free deep optics for depth estimation with precise simulation, Optics and Lasers in Engineering 2024
- Du2Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels, ECCV 2022
- Dual pixel exploration: Simultaneous depth estimation and image restoration, CVPR 2021 | github
- Learning single camera depth estimation using dual-pixels, ICCV 2019 | github
- Modeling Defocus-Disparity in Dual-Pixel Sensors, ICCP 2020 | github
Fisheye
360 deg Depth
- CRF360D: Monocular 360 Depth Estimation via Neural Spherical Fully-Connected CRFs, arxiv 2024
- Distortion-Aware Self-Supervised Indoor 360∘ Depth Estimation via Hybrid Projection Fusion and Structural Regularities, TMM 2023
- PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation, ECCV 2022 | github
- Omnifusion: 360 monocular depth estimation via geometry-aware fusion, CVPR 2022 | github
Sparse Depth Completion
- LRRU: Long-short Range Recurrent Updating Networks for Depth Completion, ICCV 2023 | github
- BEV@DC: Bird's-Eye View Assisted Training for Depth Completion, CVPR 2023
- MFF-Net: Towards Efficient Monocular Depth Completion With Multi-Modal Feature Fusion, RAL 2023
- CompletionFormer: Depth Completion with Convolutions and Vision Transformers, CVPR 2023 | github
- Dynamic Spatial Propagation Network for Depth Completion, AAAI 2022 | github
- CostDCNet: Cost Volume based Depth Completion for a Single RGB-D Image, ECCV 2022 | github
- Monitored Distillation for Positive Congruent Depth Completion, ECCV 2022 | github
- RigNet: Repetitive Image Guided Network for Depth Completion, ECCV 2022
- PENet: Towards Precise and Efficient Image Guided Depth Completion, ICRA 2021 | github
- Scene Completeness-Aware Lidar Depth Completion for Driving Scenario, ICASSP 2021 | github
- Non-Local Spatial Propagation Network for Depth Completion, ECCV 2020 | github
- Depth Completion From Sparse LiDAR Data With Depth-Normal Constraints, ICCV 2019 | github
- DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth Completion, ITSC 2019 | github
- Deep RGB-D canonical correlation analysis for sparse depth completion, NeurIPS 2019 | github
Indoor Datasets
Indoor dataset with a focus on space type