Papers with Code 아카이브
Stereo Matching
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Stereo Matching is one of the core technologies in computer vision, which recovers 3D structures of real world from 2D images. It has been widely used in areas such as autonomous driving, augmented reality and robotics navigation. Given a pair of rectified stereo images, the goal of Stereo Matching is to compute the disparity for each pixel in the reference image, where disparity is defined as the horizontal displacement between a pair of corresponding pixels in the left and right images.
Source: Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Real-time Dense Reconstruction of Tissue Surface from Stereo Optical Video
A Multi-spectral Dataset for Evaluating Motion Estimation Systems
MTStereo 2.0: improved accuracy of stereo depth estimation withMax-trees
A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding
PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching
Content-Aware Inter-Scale Cost Aggregation for Stereo Matching
FP-Stereo: Hardware-Efficient Stereo Vision for Embedded Applications
A Survey on Deep Learning Techniques for Stereo-based Depth Estimation
A Nearest Neighbor Network to Extract Digital Terrain Models from 3D Point Clouds
Noise-Sampling Cross Entropy Loss: Improving Disparity Regression Via Cost Volume Aware Regularizer
Epipolar Transformers
StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching
Deep 3D Portrait from a Single Image
Expanding Sparse Guidance for Stereo Matching
LSM: Learning Subspace Minimization for Low-level Vision
AANet: Adaptive Aggregation Network for Efficient Stereo Matching
On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: a Survey
AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching
Beyond Photometric Consistency: Gradient-based Dissimilarity for Improving Visual Odometry and Stereo Matching
Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching
Du$^2$Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels
Superpixel Segmentation with Fully Convolutional Networks
FADNet: A Fast and Accurate Network for Disparity Estimation
Scene Completeness-Aware Lidar Depth Completion for Driving Scenario
Uncertainty Estimation for End-To-End Learned Dense Stereo Matching via Probabilistic Deep Learning
A Robust Real-Time Computing-based Environment Sensing System for Intelligent Vehicle
Active Perception with A Monocular Camera for Multiscopic Vision
Depth-Based Selective Blurring in Stereo Images Using Accelerated Framework
A hybrid algorithm for disparity calculation from sparse disparity estimates based on stereo vision
Correcting Decalibration of Stereo Cameras in Self-Driving Vehicles
Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
Hierarchical Deep Stereo Matching on High-resolution Images
Sub-pixel matching method for low-resolution thermal stereo images
Domain-invariant Stereo Matching Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.