Unsupervised 3D Reconstruction with Multi-Measure and High-Resolution Loss
Multi-view 3D reconstruction technology based on deep learning is developing rapidly. Unsupervised learning has become a research hotspot because it does not need ground truth labels. The current unsupervised method mainly uses 3DCNN to regularize the cost volume to regression image depth. This appr...
Main Authors: | Yijie Zheng, Jianxin Luo, Weiwei Chen, Yanyan Zhang, Haixun Sun, Zhisong Pan |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/1/136 |
Similar Items
-
Semantically Derived Geometric Constraints for MVS Reconstruction of Textureless Areas
by: Elisavet Konstantina Stathopoulou, et al.
Published: (2021-03-01) -
KD-PatchMatch: A Self-Supervised Training Learning-Based PatchMatch
by: Qingyu Tan, et al.
Published: (2023-02-01) -
MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application
by: Qingsong Yan, et al.
Published: (2024-03-01) -
Accelerated Multi-View Stereo for 3D Reconstruction of Transmission Corridor with Fine-Scale Power Line
by: Wei Huang, et al.
Published: (2021-10-01) -
CrossPatch-Based Rolling Label Expansion for Dense Stereo Matching
by: Huaiyuan Xu, et al.
Published: (2020-01-01)