论文标题
SFM-TTR：使用运动结构来测试单视深网的测试时间细化
SfM-TTR: Using Structure from Motion for Test-Time Refinement of Single-View Depth Networks
论文作者
论文摘要
从单个视图估算密集的深度图是几何形式的，最新的方法依赖于学习深度使用深层神经网络与视觉外观的关系。另一方面，运动（SFM）的结构利用多视图约束来产生非常准确但稀疏的地图，因为跨图像的匹配通常受局部判别性纹理的限制。在这项工作中，我们通过提出一种新型的测试时间改进（TTR）方法（称为SFM-TTR）结合了两种方法的优势，从而提高了使用SFM多视图提示在测试时间的单视深网络的性能。具体而言，与艺术的状态不同，我们使用稀疏的SFM点云作为测试时间自我提出的信号，对网络编码器进行微调以学习测试场景的更好表示。我们的结果表明，将SFM-TTR添加到几个最先进的自我监管和监督网络中如何显着提高其性能，这主要优于先前的TTR基线，主要基于光度计多视图一致性。该代码可在https://github.com/serizba/sfm-ttr上找到。
Estimating a dense depth map from a single view is geometrically ill-posed, and state-of-the-art methods rely on learning depth's relation with visual appearance using deep neural networks. On the other hand, Structure from Motion (SfM) leverages multi-view constraints to produce very accurate but sparse maps, as matching across images is typically limited by locally discriminative texture. In this work, we combine the strengths of both approaches by proposing a novel test-time refinement (TTR) method, denoted as SfM-TTR, that boosts the performance of single-view depth networks at test time using SfM multi-view cues. Specifically, and differently from the state of the art, we use sparse SfM point clouds as test-time self-supervisory signal, fine-tuning the network encoder to learn a better representation of the test scene. Our results show how the addition of SfM-TTR to several state-of-the-art self-supervised and supervised networks improves significantly their performance, outperforming previous TTR baselines mainly based on photometric multi-view consistency. The code is available at https://github.com/serizba/SfM-TTR.
