qq_43307074的博客

【论文简述】HAMMER：Learning Entropy Maps to Create Accurate 3D Models in Multi-View Stereo（WACV 2024）

【论文简述】GC-MVSNet Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo（WACV 2024）

Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo（AAAI 2024）

【论文简述】MVSFormer++ Revealing the Devil in Transformer’s Details for Multi-View Stereo（ICLR 2024）

【论文简述】Multi-sensor large-scale dataset for multi-view 3D reconstruction（CVPR 2023）

【论文简述】GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation（PAMI 2022）

【论文简述】Multi-View Guided Multi-View Stereo（IROS 2022）

Occlusion-Aware Depth Estimation withAdaptive Normal Constraints（ECCV 2020）

【论文简述】High-frequency Stereo Matching Network（CVPR 2023）

【论文简述】Uncertainty awareness with adaptive propagation for mvs(Applied Intelligence 2023）

【论文简述】Adaptive region aggregation for MVS matching using deformable convolutional network（2023）

【论文简述】Bi-ClueMVSNet: Learning Bidirectional OcclusionClues for Multi-View Stereo（IJCNN 2023）

【论文简述】N2MVSNet: Non-Local Neighbors Aware Multi-View Stereo Network（ICASSP 2023）

【论文简述】When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo（ICCV 2023）

【论文简述】A-SATMVSNet: Anattention-aware multi-viewstereo matching network based on satellie imagery

【论文简述】Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity（AAAI 2023）

【论文简述】DSC-MVSNet: attention aware cost volume regularization based ondepthwise separable（CIS 2023）

【论文简述】CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo（IJCAI 2023）

【论文简述】NR-MVSNet Learning Multi-View Stereo Basedon Normal Consistency and Depth Refinement（TIP 2023）

【论文简述】Constraining Depth Map Geometry for Multi-View Stereo A Dual-Depth Approach with Saddle-shaped Depth Cells（ICCV 2023）

【论文简述】Context-Guided Multi-view Stereo with Depth Back-Projection（MMM 2023）

【论文简述】Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation（AAAI 2023）

【论文简述】Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo（CVPR 2023）

【论文简述】GigaMVS: A Benchmark for Ultra-large-scale Gigapixel-level 3D Reconstruction（TPAMI 2021）

【论文简述】IS-MVSNet:Importance Sampling-based MVSNet（ECCV 2022）

【论文简述】GeoMVSNet: Learning Multi-View Stereo with Geometry Perception（CVPR 2023）

【论文简述】Multi-View Stereo Representation Revisit: Region-Aware MVSNet（CVPR 2023）

【论文简述】Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentat（AAAI 2021）

【论文简述】WT-MVSNet: Window-based Transformers forMulti-view Stereo（arxiv 2023）

【论文简述】Learning Inverse Depth Regression for Pixelwise Visibility-AwareMulti-View Stereo （IJCV 2022）

【论文简述】ATLAS-MVSNet: Attention Layers for Feature Extraction and Cost Volume Regularization in Multi-View Stereo（ICPR 2022）

【论文简述】Non-parametric Depth Distribution Modelling based Depth Inference forMulti-view St（CVPR 2022）

【论文简述】DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo（WACV 2023）

【论文简述】Multi-View Stereo Vision Patchmatch Algorithm Based onData Augmentation（sensors 2023）

【论文简述】OcclusionFusion: Occlusion-aware Motion Estimationfor Real-time Dynamic 3D Recons（CVPR 2022）

【论文简述】Iterative Geometry Encoding Volume for Stereo Matching and Multi-View Stereo（CVPR 2023）

给定深度不一致的两层3D代价体f eature_x, f eature_y∈C×D×H×W，首先将它们输入一个步幅为1 × 1 × 1的卷积层，分别生成两个新的特征图Xout和Yout。因此，特征图像包含了丰富的局部和全局特征信息。GCCN在3D CNN回归代价体计算中引入了一种有效的上下文特征互补学习模块(CCLM)策略，可以互补学习两个不同深度的输入代价体的特征。F−XY为输入的3D代价体f eature_x和f eature_y的相关系数矩阵，Fsa−XY为上下文特征互补学习模块后输出的3D代价体。

【论文简述】Curvature-guided dynamic scale networks for Multi-view Stereo（ ICLR 2022）

【论文简述】Multi-View Stereo with Transformer（arxiv 2021）

【论文简述】Generalized Binary Search Network for Highly-Efficient Multi-View Stereo（CVPR 2022）