SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation | ✓ Link | 0.029 | 1.394 | 0.069 | 0.048 | 0.99 | 0.999 | 1.000 | | SPIDepth | 2024-04-18 |
UniK3D: Universal Camera Monocular 3D Estimation | ✓ Link | 0.037 | 1.68 | | 0.060 | 0.990 | 0.998 | 0.999 | | UniK3D (FT, metric) | 2025-03-20 |
UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler | ✓ Link | 0.037 | 1.71 | | 0.061 | 0.989 | 0.998 | 0.999 | | UniDepthV2 (FT, metric) | 2025-02-27 |
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation | ✓ Link | 0.039 | 1.766 | | 0.060 | 0.989 | 0.998 | 1.000 | | Metric3Dv2 (g2, FT, 80m, flip_aug_test) | 2024-03-22 |
LightedDepth: Video Depth Estimation in Light of Limited Inference View Angles | ✓ Link | 0.041 | 1.748 | 0.107 | 0.059 | 0.989 | 0.998 | 0.999 | | LightedDepth (Video Method) | 2023-01-01 |
FutureDepth: Learning to Predict the Future Improves Video Depth Estimation | | 0.041 | 1.856 | 0.117 | 0.066 | 0.984 | 0.998 | 1.000 | 0.117 | FutureDepth | 2024-03-19 |
UniDepth: Universal Monocular Metric Depth Estimation | ✓ Link | 0.042 | 1.75 | | 0.064 | 0.986 | 0.998 | 0.999 | | UniDepth (Zero-shot) | 2024-03-27 |
SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimation | ✓ Link | 0.043 | 1.698 | 0.105 | 0.064 | 0.983 | 0.998 | 0.999 | | SQLdepth (ConvNeXt-L) | 2023-09-01 |
Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving | ✓ Link | 0.044 | 1.712 | 0.132 | 0.069 | 0.980 | 0.997 | 0.999 | | AFNet | 2024-03-12 |
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data | ✓ Link | 0.046 | 1.896 | 0.121 | 0.069 | 0.982 | 0.998 | 1.000 | | Depth Anything | 2024-01-19 |
Harnessing Diffusion Models for Visual Perception with Meta Prompts | ✓ Link | 0.047 | 1.928 | 0.125 | 0.071 | 0.981 | 0.998 | 1.000 | | MetaPrompt-SD | 2023-12-22 |
ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation | ✓ Link | 0.048 | 1.966 | 0.139 | 0.074 | 0.979 | 0.998 | 1.000 | | ECoDepth | 2024-03-27 |
ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation | ✓ Link | 0.048 | 1.987 | 0.136 | 0.073 | 0.98 | 0.998 | 1.000 | | ScaleDepth-K | 2024-07-11 |
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment | ✓ Link | 0.048 | 2.015 | 0.136 | 0.073 | 0.980 | 0.998 | 1.000 | | EVP | 2023-12-13 |
GEDepth: Ground Embedding for Monocular Depth Estimation | ✓ Link | 0.048 | 2.044 | 0.142 | 0.076 | 0.9763 | 0.9972 | 0.9993 | | GEDepth | 2023-09-18 |
MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation | | 0.049 | 1.984 | 0.13 | 0.072 | 0.977 | 0.998 | 0.9995 | | MAMo | 2023-07-26 |
Revealing the Dark Secrets of Masked Image Modeling | ✓ Link | 0.050 | 1.966 | 0.139 | 0.075 | 0.977 | 0.998 | 1.000 | | SwinV2-L 1K-MIM | 2022-05-26 |
IEBins: Iterative Elastic Bins for Monocular Depth Estimation | ✓ Link | 0.050 | 2.011 | 0.142 | 0.075 | 0.978 | 0.998 | 0.999 | | IEBins | 2023-09-25 |
NDDepth: Normal-Distance Assisted Monocular Depth Estimation | ✓ Link | 0.050 | 2.025 | 0.141 | 0.075 | 0.978 | 0.998 | 0.999 | | NDDepth | 2023-09-19 |
URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation | ✓ Link | 0.050 | 2.032 | 0.142 | 0.076 | 0.977 | 0.997 | 0.999 | | URCDC-Depth | 2023-02-16 |
iDisc: Internal Discretization for Monocular Depth Estimation | ✓ Link | 0.050 | 2.067 | 0.145 | 0.077 | 0.977 | 0.997 | 0.999 | | iDisc | 2023-04-13 |
DDP: Diffusion Model for Dense Visual Prediction | ✓ Link | 0.050 | 2.072 | 0.148 | 0.076 | 0.975 | 0.997 | 0.999 | | DDP (Swin-L, step-3) | 2023-03-30 |
Analysis of NaN Divergence in Training Monocular Depth Estimation Model | | 0.0508 | 2.0373 | 0.1458 | 0.077 | 0.9757 | 0.9974 | 0.9994 | | MIM-Swin-V2 | 2023-11-07 |
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention | ✓ Link | 0.051 | 2.081 | 0.149 | 0.077 | 0.976 | 0.997 | 0.999 | | PixelFormer | 2022-10-17 |
Revealing the Dark Secrets of Masked Image Modeling | ✓ Link | 0.052 | 2.050 | 0.148 | 0.078 | 0.976 | 0.998 | 0.999 | | SwinV2-B 1K-MIM | 2022-05-26 |
BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation | ✓ Link | 0.052 | 2.098 | 0.151 | 0.079 | 0.974 | 0.997 | 0.999 | | BinsFormer | 2022-04-03 |
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation | ✓ Link | 0.052 | 2.129 | 0.155 | 0.079 | 0.974 | 0.997 | 0.999 | | NeWCRFs | 2022-03-03 |
DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation | ✓ Link | 0.052 | 2.143 | 0.158 | 0.079 | 0.975 | 0.997 | 0.999 | | DepthFormer | 2022-03-27 |
Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision | ✓ Link | 0.053 | 2.101 | 0.161 | 0.082 | 0.969 | 0.996 | 0.999 | | MonoDELSNet | 2021-03-22 |
Deep Two-View Structure-from-Motion Revisited | ✓ Link | 0.055 | 2.273 | 0.224 | | | | | | SfM-Revisited | 2021-04-01 |
D-Net: A Generalised and Optimised Deep Network for Monocular Depth Estimation | ✓ Link | 0.056 | 2.362 | 0.189 | 0.087 | 0.963 | 0.995 | 0.999 | | D-Net | 2021-09-29 |
Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth | ✓ Link | 0.057 | 2.297 | | 0.086 | 0.967 | 0.996 | 0.999 | | GLPDepth | 2022-01-19 |
NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis | | 0.057 | 2.702 | | | | | | | NVS-MonoDepth | 2021-12-22 |
Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion | ✓ Link | 0.058 | 2.285 | 0.187 | 0.087 | 0.967 | 0.996 | 0.999 | | Depthformer | 2022-07-10 |
AdaBins: Depth Estimation using Adaptive Bins | ✓ Link | 0.058 | 2.360 | | 0.088 | 0.964 | 0.995 | 0.999 | | AdaBins | 2020-11-28 |
Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image | ✓ Link | 0.058 | 2.77 | | | 0.967 | 0.995 | 0.999 | | Metric3D (zero-shot) | 2023-07-20 |
Monocular Depth Estimation Using Laplacian Pyramid-Based Depth Residuals | ✓ Link | 0.059 | 2.446 | | 0.091 | 0.962 | 0.994 | 0.999 | | LapDepth | 2021-01-08 |
Vision Transformers for Dense Prediction | ✓ Link | 0.062 | 2.573 | | 0.092 | 0.959 | 0.995 | 0.999 | | DPT-Hybrid | 2021-03-24 |
From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation | ✓ Link | 0.064 | | | | | | | | BTS | 2019-07-24 |
DINOv2: Learning Robust Visual Features without Supervision | ✓ Link | 0.0652 | 2.1128 | 0.1797 | 0.0882 | 0.968 | 0.997 | 0.9993 | | DINOv2 (ViT-g/14 frozen, w/ DPT decoder) | 2023-04-14 |
LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learning | ✓ Link | 0.070 | 2.923 | | | | | | | LightDepth | 2022-11-16 |
Deep Ordinal Regression Network for Monocular Depth Estimation | ✓ Link | 0.072 | 2.727 | | 0.120 | 0.932 | 0.984 | 0.994 | | DORN | 2018-06-06 |
Enforcing geometric constraints of virtual normal for depth prediction | ✓ Link | 0.072 | | | | | | | | VNL | 2019-07-29 |
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage | ✓ Link | 0.073 | | | | 0.953 | | | | PrimeDepth + Depth Anything | 2024-09-13 |
On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation | | 0.075 | | | | | | | | DSN | 2020-10-13 |
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage | ✓ Link | 0.079 | | | | 0.937 | | | | PrimeDepth | 2024-09-13 |
Focal-WNet: An Architecture Unifying Convolution and Attention for Depth Estimation | ✓ Link | 0.082 | 3.076 | | 0.120 | 0.926 | 0.986 | 0.997 | | Focal-WNet | 2022-07-18 |
DepthMaster: Taming Diffusion Models for Monocular Depth Estimation | ✓ Link | 0.082 | | | | 0.937 | | | | DepthMaster | 2025-01-05 |
Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic Scenes | ✓ Link | 0.091 | 4.232 | 0.170 | 0.649 | 0.909 | 0.968 | 0.984 | | Manydepth2 | 2023-12-23 |
Enhancing self-supervised monocular depth estimation with traditional visual odometry | | 0.091 | | | | | | | | VOMonodepth | 2019-08-08 |
High Quality Monocular Depth Estimation via Transfer Learning | ✓ Link | 0.093 | | | | | | | | DenseDepth | 2018-12-31 |
Single View Stereo Matching | ✓ Link | 0.094 | | | | | | | | SVS | 2018-03-07 |
Learning monocular depth estimation infusing traditional stereo knowledge | ✓ Link | 0.096 | | | | | | | | monoResMatch | 2019-04-08 |
Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network | ✓ Link | 0.096 | | | | | | | | SemiDepth | 2019-05-18 |
Monocular Depth Estimation by Learning from Heterogeneous Datasets | | 0.096 | | | | | | | | CFA | 2018-03-21 |
Self-Supervised Monocular Depth Hints | ✓ Link | 0.096 | | | | | | | | Depth Hints | 2019-09-19 |
Structure-Attentioned Memory Network for Monocular Depth Estimation | | 0.097 | | | | | | | | SOM | 2019-09-10 |
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation | ✓ Link | 0.099 | 3.304 | | 0.138 | 0.916 | 0.987 | 0.996 | | Marigold | 2023-12-04 |
GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Network | ✓ Link | 0.104 | 4.494 | | 0.181 | 0.888 | 0.965 | 0.984 | | GCNDepth | 2021-12-13 |
Digging Into Self-Supervised Monocular Depth Estimation | ✓ Link | 0.106 | | | | | | | | monodepth2 M | 2018-06-04 |
Single Image Depth Estimation Trained via Depth from Defocus Cues | ✓ Link | 0.110 | | | | | | | | DeepLabV3+ (F10) | 2020-01-14 |
DiPE: Deeper into Photometric Errors for Unsupervised Learning of Depth and Ego-motion from Monocular Videos | ✓ Link | 0.112 | | | | | | | | DiPE | 2020-03-03 |
Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving Applications | ✓ Link | 0.113 | 4.812 | | 0.191 | 0.877 | 0.960 | 0.981 | | DNet | 2020-04-12 |
Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation | ✓ Link | 0.113 | | | | | | | | LSIM | 2019-05-01 |
Unsupervised Scale-consistent Depth Learning from Video | ✓ Link | 0.114 | 4.706 | | 0.191 | 0.873 | 0.960 | 0.982 | | SC-Depth (ResNet 50) | 2021-05-25 |
Towards Scene Understanding: Unsupervised Monocular Depth Estimation With Semantic-Aware Representation | | 0.118 | | | | | | | | SemanticAware | 2019-06-01 |
Unsupervised Scale-consistent Depth Learning from Video | ✓ Link | 0.119 | 4.950 | | 0.197 | 0.863 | 0.957 | 0.981 | | SC-Depth (ResNet18) | 2021-05-25 |
3D Packing for Self-Supervised Monocular Depth Estimation | ✓ Link | 0.12 | | | | | | | | PackNet-SfM | 2019-05-06 |
Learning monocular depth estimation with unsupervised trinocular assumptions | ✓ Link | 0.126 | | | | | | | | 3Net | 2018-08-05 |
Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video | ✓ Link | 0.128 | | | | | | | | SC-SfMLearner_CS+K | 2019-08-28 |
Self-supervised Learning for Single View Depth and Surface Normal Estimation | | 0.133 | | | | | | | | SelfDepthNorm | 2019-03-01 |
SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception | ✓ Link | 0.133 | | | | | | | | SIGNet | 2018-12-13 |
Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos | ✓ Link | 0.135 | | | | | | | | struct2depth | 2018-11-15 |
Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video | ✓ Link | 0.137 | | | | | | | | SC-SfMLearner | 2019-08-28 |
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation | ✓ Link | 0.140 | | | | | | | | CC | 2018-05-24 |
Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings | | 0.14 | | | | | | | | SIW | 2022-02-04 |
Learning to Recover 3D Scene Shape from a Single Image | ✓ Link | 0.149 | | | | 0.784 | | | | LeReS | 2020-12-17 |
Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation | ✓ Link | 0.149 | | | | | | | | GASDA | 2019-04-03 |
Veritatem Dies Aperit- Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach | ✓ Link | 0.193 | | | | | | | | VDA | 2019-03-26 |