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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem
Lightweight Monocular Depth Estimation with an Edge Guided Network
UDepth: Fast Monocular Depth Estimation for Visually-guided Underwater Robots
Image-to-Image Translation for Autonomous Driving from Coarsely-Aligned Image Pairs
On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimation
3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling
Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimation
BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation
LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile Devices
Rethinking Skip Connections in Encoder-decoder Networks for Monocular Depth Estimation
Dense Depth Distillation with Out-of-Distribution Simulated Images
Depth Map Decomposition for Monocular Depth Estimation
DepthFake: a depth-based strategy for detecting Deepfake videos
Multi-task Learning for Monocular Depth and Defocus Estimations with Real Images
MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer
TransDSSL: Transformer based Depth Estimation via Self-Supervised Learning
Gradient-based Uncertainty for Monocular Depth Estimation
Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter
Learning Feature Decomposition for Domain Adaptive Monocular Depth Estimation
RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation
Latent Discriminant deterministic Uncertainty
MonoIndoor++:Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments
Focal-WNet: An Architecture Unifying Convolution and Attention for Depth Estimation
Adversarial Attacks on Monocular Pose Estimation
Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics
Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
Depthformer : Multiscale Vision Transformer For Monocular Depth Estimation With Local Global Information Fusion
BlindSpotNet: Seeing Where We Cannot See
DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning
False Negative Reduction in Semantic Segmentation under Domain Shift using Depth Estimation
PS$^2$F: Polarized Spiral Point Spread Function for Single-Shot 3D Sensing
Can Language Understand Depth?
Recovering Detail in 3D Shapes Using Disparity Maps
MGNet: Monocular Geometric Scene Understanding for Autonomous Driving
Monocular Depth Decomposition of Semi-Transparent Volume Renderings
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.