Learning to Adapt Multi-View Stereo by Self-Supervision
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, self-supervised methods are favourable since they do not rely on ground truth data which would be needed for supervised training and is often difficult to obtain. Moreover, learned multi-view stereo reconstruction is prone to environment changes and should robustly generalise to different domains. We propose an adaptive learning approach for multi-view stereo which trains a deep neural network for improved adaptability to new target domains. We use model-agnostic meta-learning (MAML) to train base parameters which, in turn, are adapted for multi-view stereo on new domains through self-supervised training. Our evaluations demonstrate that the proposed adaptation method is effective in learning self-supervised multi-view stereo reconstruction in new domains.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Scene ReconstructionMeta-LearningSimilar Papers 제목 키워드 기반
Digging into Uncertainty in Self-supervised Multi-view Stereo
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 LearningSelf-supervised Learning of Depth Inference for Multi-view Stereo
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 LearningLearning multiplane images from single views with self-supervision
Generating static novel views from an already captured image is a hard task in computer vision and graphics, in particular when the single input image has dynamic parts such as persons or moving objects. In this paper, w…
Monocular Depth Estimation with Self-supervised Instance Adaptation
Recent advances in self-supervised learning havedemonstrated that it is possible to learn accurate monoculardepth reconstruction from raw video data, without using any 3Dground truth for supervision. However, in robotics…
Depth EstimationMonocular Depth EstimationMonocular ReconstructionSelf-Supervised LearningUnsupervised Stereo via Multi-Baseline Geometry-Consistent Self-Training
Photometric loss and pseudo-label-based self-training are two widely used methods for training stereo networks on unlabeled data. However, they both struggle to provide accurate supervision in occluded regions. The forme…