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.
Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting
Extraction of Key-frames of Endoscopic Videos by using Depth Information
Fractal Pyramid Networks
Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated Scenes
SGTBN: Generating Dense Depth Maps from Single-Line LiDAR
Exploring Depth Contribution for Camouflaged Object Detection
EdgeConv with Attention Module for Monocular Depth Estimation
A Hybrid mmWave and Camera System for Long-Range Depth Imaging
Single Image Depth Prediction with Wavelet Decomposition
Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging
Unsupervised Scale-consistent Depth Learning from Video
Real-time Monocular Depth Estimation with Sparse Supervision on Mobile
M4Depth: Monocular depth estimation for autonomous vehicles in unseen environments
Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation
Boosting Light-Weight Depth Estimation Via Knowledge Distillation
The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth
Improving Online Performance Prediction for Semantic Segmentation
Domain Adaptive Monocular Depth Estimation With Semantic Information
Learning optical flow from still images
S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation
Deep Two-View Structure-from-Motion Revisited
Geometric Unsupervised Domain Adaptation for Semantic Segmentation
SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing
Vision Transformers for Dense Prediction
Revisiting Self-Supervised Monocular Depth Estimation
Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision
Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss
Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction
Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks
Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation
ADAADepth: Adapting Data Augmentation and Attention for Self-Supervised Monocular Depth Estimation
Improved Point Transformation Methods For Self-Supervised Depth Prediction
Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction
Learning Depth via Leveraging Semantics: Self-supervised Monocular Depth Estimation with Both Implicit and Explicit Semantic Guidance
Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.