Depth Estimation

777 papers with code • 13 benchmarks • 70 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.

Source: DIODE: A Dense Indoor and Outdoor DEpth Dataset

Libraries

Use these libraries to find Depth Estimation models and implementations

Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving

gandolfczjh/3d2fool 26 Mar 2024

Deep learning-based monocular depth estimation (MDE), extensively applied in autonomous driving, is known to be vulnerable to adversarial attacks.

1
26 Mar 2024

When Do We Not Need Larger Vision Models?

bfshi/scaling_on_scales 19 Mar 2024

Our results show that a multi-scale smaller model has comparable learning capacity to a larger model, and pre-training smaller models with S$^2$ can match or even exceed the advantage of larger models.

133
19 Mar 2024

FeatUp: A Model-Agnostic Framework for Features at Any Resolution

mhamilton723/FeatUp 15 Mar 2024

Deep features are a cornerstone of computer vision research, capturing image semantics and enabling the community to solve downstream tasks even in the zero- or few-shot regime.

786
15 Mar 2024

Robust Shape Fitting for 3D Scene Abstraction

fkluger/cuboids_revisited 15 Mar 2024

A RANSAC estimator guided by a neural network fits these primitives to a depth map.

31
15 Mar 2024

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

pardistaghavi/swinmtl 15 Mar 2024

This research paper presents an innovative multi-task learning framework that allows concurrent depth estimation and semantic segmentation using a single camera.

1
15 Mar 2024

SM4Depth: Seamless Monocular Metric Depth Estimation across Multiple Cameras and Scenes by One Model

1hao-liu/sm4depth 13 Mar 2024

Third, to reduce the reliance on massive training data, we propose a ``divide and conquer" solution.

24
13 Mar 2024

METER: a mobile vision transformer architecture for monocular depth estimation

lorenzopapa5/meter 13 Mar 2024

State of the art MDE models typically rely on vision transformers (ViT) architectures that are highly deep and complex, making them unsuitable for fast inference on devices with hardware constraints.

3
13 Mar 2024

Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving

junda24/afnet 12 Mar 2024

In this work, we propose a new robustness benchmark to evaluate the depth estimation system under various noisy pose settings.

40
12 Mar 2024

D4D: An RGBD diffusion model to boost monocular depth estimation

lorenzopapa5/diffusion4d 12 Mar 2024

Ground-truth RGBD data are fundamental for a wide range of computer vision applications; however, those labeled samples are difficult to collect and time-consuming to produce.

0
12 Mar 2024

Stealing Stable Diffusion Prior for Robust Monocular Depth Estimation

hitcslj/ssd 8 Mar 2024

This paper introduces a novel approach named Stealing Stable Diffusion (SSD) prior for robust monocular depth estimation.

20
08 Mar 2024