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.
DepthP+P: Metric Accurate Monocular Depth Estimation using Planar and Parallax
All in Tokens: Unifying Output Space of Visual Tasks via Soft Token
BS3D: Building-scale 3D Reconstruction from RGB-D Images
Exploring Efficiency of Vision Transformers for Self-Supervised Monocular Depth Estimation
MaskingDepth: Masked Consistency Regularization for Semi-supervised Monocular Depth Estimation
Lightweight Monocular Depth Estimation
ROIFormer: Semantic-Aware Region of Interest Transformer for Efficient Self-Supervised Monocular Depth Estimation
Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation
Event-based Monocular Dense Depth Estimation with Recurrent Transformers
3D Object Aided Self-Supervised Monocular Depth Estimation
Multi-resolution Monocular Depth Map Fusion by Self-supervised Gradient-based Composition
Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection
ObjCAViT: Improving Monocular Depth Estimation Using Natural Language Models And Image-Object Cross-Attention
3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformers
Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation
The Monocular Depth Estimation Challenge
Hybrid Transformer Based Feature Fusion for Self-Supervised Monocular Depth Estimation
A Practical Stereo Depth System for Smart Glasses
LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learning
SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes
RCDPT: Radar-Camera fusion Dense Prediction Transformer
Photo-realistic Neural Domain Randomization
Hierarchical Normalization for Robust Monocular Depth Estimation
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
MonoDVPS: A Self-Supervised Monocular Depth Estimation Approach to Depth-aware Video Panoptic Segmentation
Improving the Reliability for Confidence Estimation
Composite Learning for Robust and Effective Dense Predictions
Frequency-Aware Self-Supervised Monocular Depth Estimation
Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth Estimation
IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty
Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation
MOTSLAM: MOT-assisted monocular dynamic SLAM using single-view depth estimation
Image Masking for Robust Self-Supervised Monocular Depth Estimation
Depth Is All You Need for Monocular 3D Detection
FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.