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.
0/1 Deep Neural Networks via Block Coordinate Descent
Analysis & Computational Complexity Reduction of Monocular and Stereo Depth Estimation Techniques
Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth Maps
Self-Supervised Pre-training of Vision Transformers for Dense Prediction Tasks
Revealing the Dark Secrets of Masked Image Modeling
Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Images
Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation
Learning Monocular Depth Estimation via Selective Distillation of Stereo Knowledge
Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Driving
FisheyeDistill: Self-Supervised Monocular Depth Estimation with Ordinal Distillation for Fisheye Cameras
Outdoor Monocular Depth Estimation: A Research Review
Depth Estimation with Simplified Transformer
Monocular Depth Estimation Using Cues Inspired by Biological Vision Systems
Multi-Frame Self-Supervised Depth with Transformers
End-to-end Learning for Joint Depth and Image Reconstruction from Diffracted Rotation
HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model
SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation
P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior
Pyramid Frequency Network with Spatial Attention Residual Refinement Module for Monocular Depth Estimation
Improving Monocular Visual Odometry Using Learned Depth
BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation
Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth
Learning Structured Gaussians to Approximate Deep Ensembles
Learning Optical Flow, Depth, and Scene Flow without Real-World Labels
LocalBins: Improving Depth Estimation by Learning Local Distributions
DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation
On the Viability of Monocular Depth Pre-training for Semantic Segmentation
Learn to Adapt for Monocular Depth Estimation
Unsupervised Simultaneous Learning for Camera Re-Localization and Depth Estimation from Video
CroMo: Cross-Modal Learning for Monocular Depth Estimation
Learning Occlusion-Aware Coarse-to-Fine Depth Map for Self-supervised Monocular Depth Estimation
Distortion-Tolerant Monocular Depth Estimation On Omnidirectional Images Using Dual-cubemap
Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation
InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding
SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.