Papers with Code 아카이브

Monocular Depth Estimation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 0
평가표: 25
보존된 평가 기록: 283

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.

Source: Defocus Deblurring Using Dual-Pixel Data

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Monocular Depth Estimation

논문

Vision Transformer based Random Walk for Group Re-Identification

EndoPerfect: High-Accuracy Monocular Depth Estimation and 3D Reconstruction for Endoscopic Surgery via NeRF-Stereo Fusion

Refinement of Monocular Depth Maps via Multi-View Differentiable Rendering

RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second

EndoDepth: A Benchmark for Assessing Robustness in Endoscopic Depth Prediction

KineDepth: Utilizing Robot Kinematics for Online Metric Depth Estimation

fCOP: Focal Length Estimation from Category-level Object Priors

ViewpointDepth: A New Dataset for Monocular Depth Estimation Under Viewpoint Shifts

Self-supervised Monocular Depth Estimation with Large Kernel Attention

EventHDR: from Event to High-Speed HDR Videos and Beyond

Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation

Optical Lens Attack on Deep Learning Based Monocular Depth Estimation

Benchmarking Robustness of Endoscopic Depth Estimation with Synthetically Corrupted Data

GroCo: Ground Constraint for Metric Self-Supervised Monocular Depth

DepthART: Monocular Depth Estimation as Autoregressive Refinement Task

Depth Estimation Based on 3D Gaussian Splatting Siamese Defocus

Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

Towards Single-Lens Controllable Depth-of-Field Imaging via Depth-Aware Point Spread Functions

GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion

PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage

Advancing Depth Anything Model for Unsupervised Monocular Depth Estimation in Endoscopy

EDADepth: Enhanced Data Augmentation for Monocular Depth Estimation

TanDepth: Leveraging Global DEMs for Metric Monocular Depth Estimation in UAVs

Introducing a Class-Aware Metric for Monocular Depth Estimation: An Automotive Perspective

Plane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth Estimation

SG-MIM: Structured Knowledge Guided Efficient Pre-training for Dense Prediction

iConFormer: Dynamic Parameter-Efficient Tuning with Input-Conditioned Adaptation

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

Large Language Models Can Understanding Depth from Monocular Images

DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation Model

EvLight++: Low-Light Video Enhancement with an Event Camera: A Large-Scale Real-World Dataset, Novel Method, and More

Adversarial Manhole: Challenging Monocular Depth Estimation and Semantic Segmentation Models with Patch Attack

NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training

InSpaceType: Dataset and Benchmark for Reconsidering Cross-Space Type Performance in Indoor Monocular Depth

TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers