877 papers with code • 14 benchmarks • 72 datasets
Depth Estimation is the task of measuring the distance of each pixel relative to the camera. Depth is extracted from either monocular (single) or stereo (multiple views of a scene) images. Traditional methods use multi-view geometry to find the relationship between the images. Newer methods can directly estimate depth by minimizing the regression loss, or by learning to generate a novel view from a sequence. The most popular benchmarks are KITTI and NYUv2. Models are typically evaluated according to a RMS metric.
Benchmarks
These leaderboards are used to track progress in Depth Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
 | |||||
 | |||||
 | |||||
 | |||||
 | |||||
 | |||||
 | |||||
 | |||||
 | |||||
 | |||||
 | |||||
 | |||||
 | |||||
 |
Show all 14 benchmarks
Collapse benchmarks
Libraries
Use these libraries to find Depth Estimation models and implementations
Cityscapes 
KITTI 
ScanNet 
NYUv2 
Matterport3D 
Middlebury 
TUM RGB-D 
SUNCG 
Taskonomy 
2D-3D-S Subtasks
Most implemented papers
ialhashim/DenseDepth • 
• 31 Dec 2018
Accurate depth estimation from images is a fundamental task in many applications including scene understanding and reconstruction.
facebookresearch/dinov2 • 
• 14 Apr 2023
The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision.
iro-cp/FCRN-DepthPrediction • • 1 Jun 2016
This paper addresses the problem of estimating the depth map of a scene given a single RGB image.
mrharicot/monodepth • • CVPR 2017
Learning based methods have shown very promising results for the task of depth estimation in single images.
isl-org/DPT • • ICCV 2021
We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks.
nianticlabs/monodepth2 • • 4 Jun 2018
Per-pixel ground-truth depth data is challenging to acquire at scale.
intel-isl/MiDaS • • 2 Jul 2019
In particular, we propose a robust training objective that is invariant to changes in depth range and scale, advocate the use of principled multi-objective learning to combine data from different sources, and highlight the importance of pretraining encoders on auxiliary tasks.
cogaplex-bts/bts • • 24 Jul 2019
We show that the proposed method outperforms the state-of-the-art works with significant margin evaluating on challenging benchmarks.
tensorflow/models • • 15 Nov 2018
Models and examples built with TensorFlow
cmsflash/efficient-attention • • 4 Dec 2018
Dot-product attention has wide applications in computer vision and natural language processing.
Content
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
