现有的单眼深度估计方法在不同的场景中实现了出色的鲁棒性,但它们只能检索仿射不变的深度,最多可达到未知的规模和变化。但是,在一些基于视频的场景中,例如视频中的视频深度估计和3D场景重建,驻留在人均预测中的未知量表和偏移可能会导致深度不一致。为了解决这个问题,我们提出了一种局部加权的线性回归方法,以恢复比例并以非常稀疏的锚点的转移,从而确保沿连续帧的比例一致性。广泛的实验表明,我们的方法可以在几个零击基准测试中最多将现有最新方法的性能提高50%。此外,我们合并了超过630万个RGBD图像,以训练强大而健壮的深度模型。我们产生的Resnet50-Backbone模型甚至胜过最先进的DPT VIT-LALGE模型。结合基于几何的重建方法,我们制定了一种新的密集3D场景重建管道,该管道受益于稀疏点的比例一致性和单眼方法的鲁棒性。通过对视频进行简单的人均预测,可以恢复准确的3D场景形状。
translated by 谷歌翻译
尽管在过去几年中取得了重大进展,但使用单眼图像进行深度估计仍然存在挑战。首先,训练度量深度预测模型的训练是不算气的,该预测模型可以很好地推广到主要由于训练数据有限的不同场景。因此,研究人员建立了大规模的相对深度数据集,这些数据集更容易收集。但是,由于使用相对深度数据训练引起的深度转移,现有的相对深度估计模型通常无法恢复准确的3D场景形状。我们在此处解决此问题,并尝试通过对大规模相对深度数据进行训练并估算深度转移来估计现场形状。为此,我们提出了一个两阶段的框架,该框架首先将深度预测到未知量表并从单眼图像转移,然后利用3D点云数据来预测深度​​移位和相机的焦距,使我们能够恢复恢复3D场景形状。由于两个模块是单独训练的,因此我们不需要严格配对的培训数据。此外,我们提出了图像级的归一化回归损失和基于正常的几何损失,以通过相对深度注释来改善训练。我们在九个看不见的数据集上测试我们的深度模型,并在零拍摄评估上实现最先进的性能。代码可用:https://git.io/depth
translated by 谷歌翻译
现有的深度完成方法通常以特定的稀疏深度类型为目标,并且在任务域之间概括较差。我们提出了一种方法,可以通过各种范围传感器(包括现代手机中的范围传感器或多视图重建算法)获得稀疏/半密度,嘈杂和潜在的低分辨率深度图。我们的方法利用了在大规模数据集中训练的单个图像深度预测网络的形式的数据驱动的先验,其输出被用作我们模型的输入。我们提出了一个有效的培训计划,我们在典型的任务域中模拟各种稀疏模式。此外,我们设计了两个新的基准测试,以评估深度完成方法的普遍性和鲁棒性。我们的简单方法显示了针对最先进的深度完成方法的优越的跨域泛化能力,从而引入了一种实用的解决方案,以在移动设备上捕获高质量的深度捕获。代码可在以下网址获得:https://github.com/yvanyin/filldepth。
translated by 谷歌翻译
深度完成旨在预测从深度传感器(例如Lidars)中捕获的极稀疏图的密集像素深度。它在各种应用中起着至关重要的作用,例如自动驾驶,3D重建,增强现实和机器人导航。基于深度学习的解决方案已经证明了这项任务的最新成功。在本文中,我们首次提供了全面的文献综述,可帮助读者更好地掌握研究趋势并清楚地了解当前的进步。我们通过通过对现有方法进行分类的新型分类法提出建议,研究网络体系结构,损失功能,基准数据集和学习策略的设计方面的相关研究。此外,我们在包括室内和室外数据集(包括室内和室外数据集)上进行了三个广泛使用基准测试的模型性能进行定量比较。最后,我们讨论了先前作品的挑战,并为读者提供一些有关未来研究方向的见解。
translated by 谷歌翻译
Monocular depth prediction plays a crucial role in understanding 3D scene geometry. Although recent methods have achieved impressive progress in evaluation metrics such as the pixel-wise relative error, most methods neglect the geometric constraints in the 3D space. In this work, we show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces one simple type of geometric constraints, namely, virtual normal directions determined by randomly sampled three points in the reconstructed 3D space, we can considerably improve the depth prediction accuracy. Significantly, the byproduct of this predicted depth being sufficiently accurate is that we are now able to recover good 3D structures of the scene such as the point cloud and surface normal directly from the depth, eliminating the necessity of training new sub-models as was previously done. Experiments on two benchmarks: NYU Depth-V2 and KITTI demonstrate the effectiveness of our method and state-of-the-art performance.
translated by 谷歌翻译
Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions and occlusions. Consequently, existing methods show poor accuracy in dynamic scenes, and the estimated depth map is blurred at object boundaries because they are usually occluded in other training views. In this paper, we propose SC-DepthV3 for addressing the challenges. Specifically, we introduce an external pretrained monocular depth estimation model for generating single-image depth prior, namely pseudo-depth, based on which we propose novel losses to boost self-supervised training. As a result, our model can predict sharp and accurate depth maps, even when training from monocular videos of highly-dynamic scenes. We demonstrate the significantly superior performance of our method over previous methods on six challenging datasets, and we provide detailed ablation studies for the proposed terms. Source code and data will be released at https://github.com/JiawangBian/sc_depth_pl
translated by 谷歌翻译
近年来,尤其是在户外环境中,自我监督的单眼深度估计已取得了重大进展。但是,在大多数现有数据被手持设备捕获的室内场景中,深度预测结果无法满足。与室外环境相比,使用自我监督的方法估算室内环境的单眼视频深度,导致了两个额外的挑战:(i)室内视频序列的深度范围在不同的框架上有很大变化,使深度很难进行。网络以促进培训的一致深度线索; (ii)用手持设备记录的室内序列通常包含更多的旋转运动,这使姿势网络难以预测准确的相对摄像头姿势。在这项工作中,我们通过对这些挑战进行特殊考虑并巩固了一系列良好实践,以提高自我监督的单眼深度估计室内环境的表现,从而提出了一种新颖的框架单声道++。首先,提出了具有基于变压器的比例回归网络的深度分解模块,以明确估算全局深度尺度因子,预测的比例因子可以指示最大深度值。其次,我们不像以前的方法那样使用单阶段的姿势估计策略,而是建议利用残留姿势估计模块来估计相对摄像机在连续迭代的跨帧中构成。第三,为了为我们的残留姿势估计模块纳入广泛的坐标指南,我们建议直接在输入上执行坐标卷积编码,以实现姿势网络。提出的方法在各种基准室内数据集(即Euroc Mav,Nyuv2,扫描仪和7片)上进行了验证,证明了最先进的性能。
translated by 谷歌翻译
现代计算机视觉已超越了互联网照片集的领域,并进入了物理世界,通过非结构化的环境引导配备摄像头的机器人和自动驾驶汽车。为了使这些体现的代理与现实世界对象相互作用,相机越来越多地用作深度传感器,重建了各种下游推理任务的环境。机器学习辅助的深度感知或深度估计会预测图像中每个像素的距离。尽管已经在深入估算中取得了令人印象深刻的进步,但仍然存在重大挑战:(1)地面真相深度标签很难大规模收集,(2)通常认为相机信息是已知的,但通常是不可靠的,并且(3)限制性摄像机假设很常见,即使在实践中使用了各种各样的相机类型和镜头。在本论文中,我们专注于放松这些假设,并描述将相机变成真正通用深度传感器的最终目标的贡献。
translated by 谷歌翻译
Monocular depth estimation is a challenging problem on which deep neural networks have demonstrated great potential. However, depth maps predicted by existing deep models usually lack fine-grained details due to the convolution operations and the down-samplings in networks. We find that increasing input resolution is helpful to preserve more local details while the estimation at low resolution is more accurate globally. Therefore, we propose a novel depth map fusion module to combine the advantages of estimations with multi-resolution inputs. Instead of merging the low- and high-resolution estimations equally, we adopt the core idea of Poisson fusion, trying to implant the gradient domain of high-resolution depth into the low-resolution depth. While classic Poisson fusion requires a fusion mask as supervision, we propose a self-supervised framework based on guided image filtering. We demonstrate that this gradient-based composition performs much better at noisy immunity, compared with the state-of-the-art depth map fusion method. Our lightweight depth fusion is one-shot and runs in real-time, making our method 80X faster than a state-of-the-art depth fusion method. Quantitative evaluations demonstrate that the proposed method can be integrated into many fully convolutional monocular depth estimation backbones with a significant performance boost, leading to state-of-the-art results of detail enhancement on depth maps.
translated by 谷歌翻译
使用从未标识的视频培训的CNNS的单视深度估计显示了重要的承诺。然而,街头场景驾驶场景中主要获得了优异的结果,并且此类方法通常在其他设置中失败,特别是手持设备采取的室内视频。在这项工作中,我们建立了手持式环境中展出的复杂自我动作是学习深度的关键障碍。我们的基本分析表明,旋转在训练期间的噪声表现在训练期间,而不是提供监督信号的翻译(基线)。为了解决挑战,我们提出了一种数据预处理方法,可以通过去除其有效学习的相对旋转来整流训练图像。显着提高的性能验证了我们的动机。在不需要预处理的情况下,我们向端到端学习,我们提出了一种具有新型损失功能的自动整流网络,可以自动学习在训练期间纠正图像。因此,我们的结果在挑战NYUV2数据集中的大幅度上以较大的余量优于先前的无监督的SOTA方法。我们还展示了我们在Scannet和Make3D中培训模型的概括,以及我们提出的7场景和基蒂数据集的建议学习方法的普遍性。
translated by 谷歌翻译
作为许多自主驾驶和机器人活动的基本组成部分,如自我运动估计,障碍避免和场景理解,单眼深度估计(MDE)引起了计算机视觉和机器人社区的极大关注。在过去的几十年中,已经开发了大量方法。然而,据我们所知,对MDE没有全面调查。本文旨在通过审查1970年至2021年之间发布的197个相关条款来弥补这一差距。特别是,我们为涵盖各种方法的MDE提供了全面的调查,介绍了流行的绩效评估指标并汇总公开的数据集。我们还总结了一些代表方法的可用开源实现,并比较了他们的表演。此外,我们在一些重要的机器人任务中审查了MDE的应用。最后,我们通过展示一些有希望的未来研究方向来结束本文。预计本调查有助于读者浏览该研究领域。
translated by 谷歌翻译
在本文中,我们串联串联一个实时单手抄语和密集的测绘框架。对于姿势估计,串联基于关键帧的滑动窗口执行光度束调整。为了增加稳健性,我们提出了一种新颖的跟踪前端,使用从全局模型中呈现的深度图来执行密集的直接图像对齐,该模型从密集的深度预测逐渐构建。为了预测密集的深度映射,我们提出了通过分层构造具有自适应视图聚合的3D成本卷来平衡关键帧之间的不同立体声基线的3D成本卷来使用整个活动密钥帧窗口的级联视图 - 聚合MVSNet(CVA-MVSNET)。最后,将预测的深度映射融合到表示为截短的符号距离函数(TSDF)体素网格的一致的全局映射中。我们的实验结果表明,在相机跟踪方面,串联优于其他最先进的传统和学习的单眼视觉径管(VO)方法。此外,串联示出了最先进的实时3D重建性能。
translated by 谷歌翻译
通过探索跨视图一致性,例如,光度计一致性和3D点云的一致性,在自我监督的单眼深度估计(SS-MDE)中取得了显着进步。但是,它们非常容易受到照明差异,遮挡,无纹理区域以及移动对象的影响,使它们不够强大,无法处理各种场景。为了应对这一挑战,我们在本文中研究了两种强大的跨视图一致性。首先,相邻帧之间的空间偏移场是通过通过可变形对齐来从其邻居重建参考框架来获得的,该比对通过深度特征对齐(DFA)损失来对齐时间深度特征。其次,计算每个参考框架及其附近框架的3D点云并转换为体素空间,在其中计算每个体素中的点密度并通过体素密度比对(VDA)损耗对齐。通过这种方式,我们利用了SS-MDE的深度特征空间和3D体素空间的时间连贯性,将“点对点”对齐范式转移到“区域到区域”。与光度一致性损失以及刚性点云对齐损失相比,由于深度特征的强大代表能力以及对上述挑战的素密度的高公差,提出的DFA和VDA损失更加强大。几个户外基准的实验结果表明,我们的方法的表现优于当前最新技术。广泛的消融研究和分析验证了拟议损失的有效性,尤其是在具有挑战性的场景中。代码和型号可在https://github.com/sunnyhelen/rcvc-depth上找到。
translated by 谷歌翻译
密集的深度和姿势估计是各种视频应用的重要先决条件。传统的解决方案遭受了稀疏特征跟踪的鲁棒性和视频中相机基线不足。因此,最近的方法利用基于学习的光流和深度在估计密集深度之前。但是,以前的作品需要大量的计算时间或产量亚最佳深度结果。我们提出了GCVD,这是本文中从运动(SFM)中基于学习的视频结构的全球一致方法。 GCVD将紧凑型姿势图集成到基于CNN的优化中,以从有效的密钥帧选择机制中实现全球一致的估计。它可以通过流动引导的密钥帧和完善的深度提高基于学习的方法的鲁棒性。实验结果表明,GCVD在深度和姿势估计上都优于最先进的方法。此外,运行时实验表明,它在提供全球一致性的短期和长期视频中都提供了强大的效率。
translated by 谷歌翻译
最近,自我监督的学习技术已经应用于计算单眼视频的深度和自我运动,实现了自动驾驶场景中的显着性能。一种广泛采用的深度和自我运动自我监督学习的假设是图像亮度在附近框架内保持恒定。遗憾的是,内窥镜场景不符合这种假设,因为在数据收集期间的照明变化,非灯泡反射和孤立性引起的严重亮度波动,并且这些亮度波动不可避免地恶化深度和自我运动估计精度。在这项工作中,我们介绍了一个新颖的概念,称为外观流动,以解决亮度不一致问题。外观流程考虑了亮度图案中的任何变型,使我们能够开发广义动态图像约束。此外,我们建立一个统一的自我监督框架,以在内窥镜场景中同时估计单眼深度和自我运动,该内窥镜场景包括结构模块,运动模块,外观模块和对应模块,以准确地重建外观并校准图像亮度。广泛的实验是在害怕的数据集和内酷数据集上进行的,拟议的统一框架超过了大幅度的其他自我监控方法。为了验证我们在不同患者和相机上的框架的泛化能力,我们训练我们的模型害怕,但在没有任何微调的情况下测试它在Serv-CT和Hamlyn数据集上,并且卓越的结果揭示了其强大的泛化能力。代码将可用:\ url {https://github.com/shuweishao/af-sfmlearner}。
translated by 谷歌翻译
The success of monocular depth estimation relies on large and diverse training sets. Due to the challenges associated with acquiring dense ground-truth depth across different environments at scale, a number of datasets with distinct characteristics and biases have emerged. We develop tools that enable mixing multiple datasets during training, even if their annotations are incompatible.In particular, we propose a robust training objective that is invariant to changes in depth range and scale, advocate the use of principled multi-objective learning to combine data from different sources, and highlight the importance of pretraining encoders on auxiliary tasks. Armed with these tools, we experiment with five diverse training datasets, including a new, massive data source: 3D films. To demonstrate the generalization power of our approach we use zero-shot cross-dataset transfer, i.e. we evaluate on datasets that were not seen during training. The experiments confirm that mixing data from complementary sources greatly improves monocular depth estimation. Our approach clearly outperforms competing methods across diverse datasets, setting a new state of the art for monocular depth estimation.
translated by 谷歌翻译
从单目视频重建3D网格的关键元素之一是生成每个帧的深度图。然而,在结肠镜检查视频重建的应用中,产生良好质量的深度估计是具有挑战性的。神经网络可以容易地被光度分散注意力欺骗,或者不能捕获结肠表面的复杂形状,预测导致破碎网格的缺陷形状。旨在从根本上提高结肠镜检查3D重建的深度估计质量,在这项工作中,我们设计了一系列培训损失来应对结肠镜检查数据的特殊挑战。为了更好的培训,使用深度和表面正常信息开发了一组几何一致性目标。而且,经典的光度损耗延伸,具有特征匹配以补偿照明噪声。随着足够强大的培训损失,我们的自我监督框架命名为COLLE,与利用先前的深度知识相比,我们的自我监督框架能够产生更好的结肠镜检查数据地图。用于重建,我们的网络能够实时重建高质量的结肠网格,而无需任何后处理,使其成为第一个在临床上适用。
translated by 谷歌翻译
Our long term goal is to use image-based depth completion to quickly create 3D models from sparse point clouds, e.g. from SfM or SLAM. Much progress has been made in depth completion. However, most current works assume well distributed samples of known depth, e.g. Lidar or random uniform sampling, and perform poorly on uneven samples, such as from keypoints, due to the large unsampled regions. To address this problem, we extend CSPN with multiscale prediction and a dilated kernel, leading to much better completion of keypoint-sampled depth. We also show that a model trained on NYUv2 creates surprisingly good point clouds on ETH3D by completing sparse SfM points.
translated by 谷歌翻译
We present a novel neural surface reconstruction method called NeuralRoom for reconstructing room-sized indoor scenes directly from a set of 2D images. Recently, implicit neural representations have become a promising way to reconstruct surfaces from multiview images due to their high-quality results and simplicity. However, implicit neural representations usually cannot reconstruct indoor scenes well because they suffer severe shape-radiance ambiguity. We assume that the indoor scene consists of texture-rich and flat texture-less regions. In texture-rich regions, the multiview stereo can obtain accurate results. In the flat area, normal estimation networks usually obtain a good normal estimation. Based on the above observations, we reduce the possible spatial variation range of implicit neural surfaces by reliable geometric priors to alleviate shape-radiance ambiguity. Specifically, we use multiview stereo results to limit the NeuralRoom optimization space and then use reliable geometric priors to guide NeuralRoom training. Then the NeuralRoom would produce a neural scene representation that can render an image consistent with the input training images. In addition, we propose a smoothing method called perturbation-residual restrictions to improve the accuracy and completeness of the flat region, which assumes that the sampling points in a local surface should have the same normal and similar distance to the observation center. Experiments on the ScanNet dataset show that our method can reconstruct the texture-less area of indoor scenes while maintaining the accuracy of detail. We also apply NeuralRoom to more advanced multiview reconstruction algorithms and significantly improve their reconstruction quality.
translated by 谷歌翻译
Photometric differences are widely used as supervision signals to train neural networks for estimating depth and camera pose from unlabeled monocular videos. However, this approach is detrimental for model optimization because occlusions and moving objects in a scene violate the underlying static scenario assumption. In addition, pixels in textureless regions or less discriminative pixels hinder model training. To solve these problems, in this paper, we deal with moving objects and occlusions utilizing the difference of the flow fields and depth structure generated by affine transformation and view synthesis, respectively. Secondly, we mitigate the effect of textureless regions on model optimization by measuring differences between features with more semantic and contextual information without adding networks. In addition, although the bidirectionality component is used in each sub-objective function, a pair of images are reasoned about only once, which helps reduce overhead. Extensive experiments and visual analysis demonstrate the effectiveness of the proposed method, which outperform existing state-of-the-art self-supervised methods under the same conditions and without introducing additional auxiliary information.
translated by 谷歌翻译