Monocular Depth Estimation
339 papers with code • 17 benchmarks • 27 datasets
Monocular Depth Estimation is the task of estimating the depth value (distance relative to the camera) of each pixel given a single (monocular) RGB image. This challenging task is a key prerequisite for determining scene understanding for applications such as 3D scene reconstruction, autonomous driving, and AR. State-of-the-art methods usually fall into one of two categories: designing a complex network that is powerful enough to directly regress the depth map, or splitting the input into bins or windows to reduce computational complexity. The most popular benchmarks are the KITTI and NYUv2 datasets. Models are typically evaluated using RMSE or absolute relative error.
Benchmarks
These leaderboards are used to track progress in Monocular Depth Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Monocular Depth Estimation models and implementationsDatasets
Cityscapes
KITTI
NYUv2
SUN RGB-D
Matterport3D
Make3D
DIODE
DDAD
Middlebury 2014
MannequinChallenge
Latest papers
Harnessing Diffusion Models for Visual Perception with Meta Prompts
Our key insight is to introduce learnable embeddings (meta prompts) to the pre-trained diffusion models to extract proper features for perception.
Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion
Nonetheless, the performance of these methods is often constrained by the domain gap and looser constraints.
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment
lavreniuk/evp
•
•
Second, we propose a novel image-text alignment module for improved feature extraction of the Stable Diffusion backbone.
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
prs-eth/marigold
•
•
Monocular depth estimation is a fundamental computer vision task.
Deeper into Self-Supervised Monocular Indoor Depth Estimation
One is the large areas of low-texture regions and the other is the complex ego-motion on indoor training datasets.
SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction
huang-yh/selfocc
•
•
Our SelfOcc outperforms the previous best method SceneRF by 58. 7% using a single frame as input on SemanticKITTI and is the first self-supervised work that produces reasonable 3D occupancy for surround cameras on nuScenes.
Camera-Independent Single Image Depth Estimation from Defocus Blur
We created a synthetic dataset which can be used to test the camera independent performance of depth from defocus blur models.
NDDepth: Normal-Distance Assisted Monocular Depth Estimation and Completion
To this end, we develop a normal-distance head that outputs pixel-level surface normal and distance.
MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion Model
Because the depth ground-truth is unavailable in the training phase, we develop a pseudo ground-truth diffusion process to assist the diffusion in MonoDiffusion.
MonoProb: Self-Supervised Monocular Depth Estimation with Interpretable Uncertainty
Self-supervised monocular depth estimation methods aim to be used in critical applications such as autonomous vehicles for environment analysis.
