paper-with-me

Papers

Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation

2021-04-12 · Hongbin Xu, Zhipeng Zhou, Yu Qiao, Wenxiong Kang, Qiuxia Wu

Recent studies have witnessed that self-supervised methods based on view synthesis obtain clear progress on multi-view stereo (MVS). However, existing methods rely on the assumption that the corresponding points among different views share the same color, which may not always be true in practice. This may lead to unreliable self-supervised signal and harm the final reconstruction performance. To address the issue, we propose a framework integrated with more reliable supervision guided by semantic co-segmentation and data-augmentation. Specially, we excavate mutual semantic from multi-view images to guide the semantic consistency. And we devise effective data-augmentation mechanism which ensures the transformation robustness by treating the prediction of regular samples as pseudo ground truth to regularize the prediction of augmented samples. Experimental results on DTU dataset show that our proposed methods achieve the state-of-the-art performance among unsupervised methods, and even compete on par with supervised methods. Furthermore, extensive experiments on Tanks&Temples dataset demonstrate the effective generalization ability of the proposed method.

📄 PDF Abstract BibTeX arXiv:2104.05374

Code (1)

ToughStoneX/Self-Supervised-MVS 공식 구현 pytorch

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

Learning to Adapt Multi-View Stereo by Self-Supervision

2020-09-28 · Arijit Mallick, Jörg Stückler, Hendrik Lensch

3D scene reconstruction from multiple views is an important classical problem in computer vision. Deep learning based approaches have recently demonstrated impressive reconstruction results. When training such models, se…

3D Scene ReconstructionMeta-Learning

Digging into Uncertainty in Self-supervised Multi-view Stereo

2021-08-30 · ICCV 2021 10 · Hongbin Xu, Zhipeng Zhou, Yali Wang, Wenxiong Kang 외

Self-supervised Multi-view stereo (MVS) with a pretext task of image reconstruction has achieved significant progress recently. However, previous methods are built upon intuitions, lacking comprehensive explanations abou…

Image ReconstructionSelf-Supervised Learning

PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching

2021-03-12 · Hengli Wang, Rui Fan, Peide Cai, Ming Liu

Supervised learning with deep convolutional neural networks (DCNNs) has seen huge adoption in stereo matching. However, the acquisition of large-scale datasets with well-labeled ground truth is cumbersome and labor-inten…

Stereo Matching

Self-supervised Learning of Depth Inference for Multi-view Stereo

2021-04-07 · CVPR 2021 1 · Jiayu Yang, Jose M. Alvarez, Miaomiao Liu

Recent supervised multi-view depth estimation networks have achieved promising results. Similar to all supervised approaches, these networks require ground-truth data during training. However, collecting a large amount o…

Depth EstimationImage ReconstructionSelf-Supervised Learning

DMS:Diffusion-Based Multi-Baseline Stereo Generation for Improving Self-Supervised Depth Estimation

2025-08-18 · Zihua Liu, Yizhou Li, Songyan Zhang, Masatoshi Okutomi arxiv

While supervised stereo matching and monocular depth estimation have advanced significantly with learning-based algorithms, self-supervised methods using stereo images as supervision signals have received relatively less…

Monocular Depth Estimation