3D Depth Estimation
12 papers with code • 1 benchmarks • 8 datasets
Image: monodepth2
Benchmarks
These leaderboards are used to track progress in 3D Depth Estimation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Datasets
HUMAN4D
DurLAR
Relative Human
Pano3D
IBISCape
Most implemented papers
Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image
mks0601/3DMPPE_POSENET_RELEASE
•
•
ICCV 2019
Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case.
Putting People in their Place: Monocular Regression of 3D People in Depth
To do so, we exploit a 3D body model space that lets BEV infer shapes from infants to adults.
MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation
vita-epfl/monoloco
•
•
ICCV 2019
We tackle the fundamentally ill-posed problem of 3D human localization from monocular RGB images.
Spherical View Synthesis for Self-Supervised 360 Depth Estimation
VCL3D/SphericalViewSynthesis
•
•
This has led to the utilization of view synthesis as an indirect objective for learning depth estimation using efficient data acquisition procedures.
Monocular, One-stage, Regression of Multiple 3D People
Through a body-center-guided sampling process, the body mesh parameters of all people in the image are easily extracted from the Mesh Parameter map.
DeepVel: deep learning for the estimation of horizontal velocities at the solar surface
aasensio/deepvel
•
•
These components are typically estimated using methods based on local correlation tracking.
CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth
jmfacil/camconvs
•
•
CVPR 2019
Single-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model.
A Deep Generative Model for Graph Layout
preddy5/A-Deep-Generative-Model-for-Graph-Layout
•
•
To provide users with an intuitive way to navigate the layout design space, we present a technique to systematically visualize a graph in diverse layouts using deep generative models.
End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
mileyan/pseudo-LiDAR_e2e
•
•
CVPR 2020
Reliable and accurate 3D object detection is a necessity for safe autonomous driving.
Coherent Reconstruction of Multiple Humans from a Single Image
JiangWenPL/multiperson
•
•
CVPR 2020
Our goal is to train a single network that learns to avoid these problems and generate a coherent 3D reconstruction of all the humans in the scene.
