Papers with Code · CC BY-SA 4.0

Depth Estimation

3D › Depth Estimation 410 평가 기록 58 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.

<span class="description-source">Source: DIODE: A Dense Indoor and Outdoor DEpth Dataset </span>

Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning

2109.10563 2021-09-22 이 페이지의 평가 1건

RMSE: 0.2776absolute relative error: 0.0649

Depth Estimation

논문

Estimating Image Depth in the Comics Domain

T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks

Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer

UniFuse: Unidirectional Fusion for 360$^{\circ}$ Panorama Depth Estimation

ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation

BiFuse: Monocular 360 Depth Estimation via Bi-Projection Fusion

BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation

DELTAS: Depth Estimation by Learning Triangulation And densification of Sparse points

Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator

Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images

FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions

Geometric Structure Based and Regularized Depth Estimation From 360 Indoor Imagery

GLPanoDepth: Global-to-Local Panoramic Depth Estimation

HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model

HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features

Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning

Learning to Recover 3D Scene Shape from a Single Image

Neural Contourlet Network for Monocular 360 Depth Estimation

OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas

OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion

PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation

PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation

SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth Estimation

SliceNet: Deep Dense Depth Estimation From a Single Indoor Panorama Using a Slice-Based Representation

SphereDepth: Panorama Depth Estimation from Spherical Domain

SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images