Erroneous feature matches have severe impact on subsequent camera pose estimation and often require additional, time-costly measures, like RANSAC, for outlier rejection. Our method tackles this challenge by addressing feature matching and pose optimization jointly. To this end, we propose a graph attention network to predict image correspondences along with confidence weights. The resulting matches serve as weighted constraints in a differentiable pose estimation. Training feature matching with gradients from pose optimization naturally learns to down-weight outliers and boosts pose estimation on image pairs compared to SuperGlue by 6.7% on ScanNet. At the same time, it reduces the pose estimation time by over 50% and renders RANSAC iterations unnecessary. Moreover, we integrate information from multiple views by spanning the graph across multiple frames to predict the matches all at once. Multi-view matching combined with end-to-end training improves the pose estimation metrics on Matterport3D by 18.8% compared to SuperGlue.
translated by 谷歌翻译
This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points. Assignments are estimated by solving a differentiable optimal transport problem, whose costs are predicted by a graph neural network. We introduce a flexible context aggregation mechanism based on attention, enabling SuperGlue to reason about the underlying 3D scene and feature assignments jointly. Compared to traditional, hand-designed heuristics, our technique learns priors over geometric transformations and regularities of the 3D world through end-to-end training from image pairs. SuperGlue outperforms other learned approaches and achieves state-of-the-art results on the task of pose estimation in challenging real-world indoor and outdoor environments. The proposed method performs matching in real-time on a modern GPU and can be readily integrated into modern SfM or SLAM systems. The code and trained weights are publicly available at github.com/magicleap/SuperGluePretrainedNetwork.
translated by 谷歌翻译
在本文中,我们建议超越建立的基于视觉的本地化方法,该方法依赖于查询图像和3D点云之间的视觉描述符匹配。尽管通过视觉描述符匹配关键点使本地化高度准确,但它具有重大的存储需求,提出了隐私问题,并需要长期对描述符进行更新。为了优雅地应对大规模定位的实用挑战,我们提出了Gomatch,这是基于视觉的匹配的替代方法,仅依靠几何信息来匹配图像键点与地图的匹配,这是轴承矢量集。我们的新型轴承矢量表示3D点,可显着缓解基于几何的匹配中的跨模式挑战,这阻止了先前的工作在现实环境中解决本地化。凭借额外的仔细建筑设计,Gomatch在先前的基于几何的匹配工作中改善了(1067m,95.7升)和(1.43m,34.7摄氏度),平均中位数姿势错误,同时需要7个尺寸,同时需要7片。与最佳基于视觉的匹配方法相比,几乎1.5/1.7%的存储容量。这证实了其对现实世界本地化的潜力和可行性,并为不需要存储视觉描述符的城市规模的视觉定位方法打开了未来努力的大门。
translated by 谷歌翻译
关键点匹配是多个图像相关应用的关键组件,例如图像拼接,视觉同时定位和映射(SLAM)等。基于手工制作和最近出现的深度学习的关键点匹配方法仅依赖于关键点和本地功能,同时在上述应用中丢失其他可用传感器(如惯性测量单元(IMU))的视觉。在本文中,我们证明IMU集成的运动估计可用于利用图像之间的关键点之前的空间分布。为此,提出了一种注意力制剂的概率视角,以自然地将空间分布集成到注意力图神经网络中。在空间分布的帮助下,可以减少用于建模隐藏特征的网络的努力。此外,我们为所提出的关键点匹配网络提出了一个投影损耗,它在匹配和未匹配的关键点之间提供了平滑的边缘。图像匹配在Visual Slam数据集上的实验表明了呈现的方法的有效性和效率。
translated by 谷歌翻译
We present a novel method for local image feature matching. Instead of performing image feature detection, description, and matching sequentially, we propose to first establish pixel-wise dense matches at a coarse level and later refine the good matches at a fine level. In contrast to dense methods that use a cost volume to search correspondences, we use self and cross attention layers in Transformer to obtain feature descriptors that are conditioned on both images. The global receptive field provided by Transformer enables our method to produce dense matches in low-texture areas, where feature detectors usually struggle to produce repeatable interest points. The experiments on indoor and outdoor datasets show that LoFTR outperforms state-of-the-art methods by a large margin. LoFTR also ranks first on two public benchmarks of visual localization among the published methods. Code is available at our project page: https://zju3dv.github.io/loftr/.
translated by 谷歌翻译
We introduce a lightweight network to improve descriptors of keypoints within the same image. The network takes the original descriptors and the geometric properties of keypoints as the input, and uses an MLP-based self-boosting stage and a Transformer-based cross-boosting stage to enhance the descriptors. The enhanced descriptors can be either real-valued or binary ones. We use the proposed network to boost both hand-crafted (ORB, SIFT) and the state-of-the-art learning-based descriptors (SuperPoint, ALIKE) and evaluate them on image matching, visual localization, and structure-from-motion tasks. The results show that our method significantly improves the performance of each task, particularly in challenging cases such as large illumination changes or repetitive patterns. Our method requires only 3.2ms on desktop GPU and 27ms on embedded GPU to process 2000 features, which is fast enough to be applied to a practical system.
translated by 谷歌翻译
Video provides us with the spatio-temporal consistency needed for visual learning. Recent approaches have utilized this signal to learn correspondence estimation from close-by frame pairs. However, by only relying on close-by frame pairs, those approaches miss out on the richer long-range consistency between distant overlapping frames. To address this, we propose a self-supervised approach for correspondence estimation that learns from multiview consistency in short RGB-D video sequences. Our approach combines pairwise correspondence estimation and registration with a novel SE(3) transformation synchronization algorithm. Our key insight is that self-supervised multiview registration allows us to obtain correspondences over longer time frames; increasing both the diversity and difficulty of sampled pairs. We evaluate our approach on indoor scenes for correspondence estimation and RGB-D pointcloud registration and find that we perform on-par with supervised approaches.
translated by 谷歌翻译
相机的估计与一组图像相关联的估计通常取决于图像之间的特征匹配。相比之下,我们是第一个通过使用对象区域来指导姿势估计问题而不是显式语义对象检测来应对这一挑战的人。我们提出了姿势炼油机网络(PosErnet),一个轻量级的图形神经网络,以完善近似的成对相对摄像头姿势。posernet利用对象区域之间的关联(简洁地表示为边界框),跨越了多个视图到全球完善的稀疏连接的视图图。我们在不同尺寸的图表上评估了7个尺寸的数据集,并展示了该过程如何有益于基于优化的运动平均算法,从而相对于基于边界框获得的初始估计,将旋转的中值误差提高了62度。代码和数据可在https://github.com/iit-pavis/posernet上找到。
translated by 谷歌翻译
在图像之间生成健壮和可靠的对应关系是多种应用程序的基本任务。为了在全球和局部粒度上捕获上下文,我们提出了Aspanformer,这是一种基于变压器的无探测器匹配器,建立在层次的注意力结构上,采用了一种新颖的注意操作,能够以自适应方式调整注意力跨度。为了实现这一目标,首先,在每个跨注意阶段都会回归流图,以定位搜索区域的中心。接下来,在中心周围生成一个采样网格,其大小不是根据固定的经验配置为固定的,而是根据与流图一起估计的像素不确定性的自适应计算。最后,在派生区域内的两个图像上计算注意力,称为注意跨度。通过这些方式,我们不仅能够维持长期依赖性,而且能够在高相关性的像素之间获得细粒度的注意,从而补偿基本位置和匹配任务中的零件平滑度。在广泛的评估基准上的最新准确性验证了我们方法的强匹配能力。
translated by 谷歌翻译
在两个图像之间建立密集对应是基本计算机视觉问题,通常通过匹配本地特征描述符来解决。然而,如果没有全球意识,这种本地特征通常不足以消除类似地区。并计算图像的成对特征相关性是计算昂贵和内存密集型。为了使本地特征意识到全球背景并提高其匹配的准确性,我们介绍了DendeGap,一种新的解决方案,以获得高效密集的信念学习,在锚点上调节图形结构化神经网络。具体地,我们首先提出利用锚点的曲线图结构,以在和图像间的情况下之前提供稀疏但可靠,并通过定向边沿传播到所有图像点。我们还通过光加权消息传递层设计了图形结构化网络以广播多级上下文,并以低内存成本生成高分辨率特征映射。最后,基于预测的特征图,我们使用循环一致性引入用于准确的对应预测的粗略框架。我们的特征描述符捕获本地和全局信息,从而启用一个连续的特征字段,用于以高分辨率查询任意点。通过对大型室内和室外数据集的全面的消融实验和评估,我们证明我们的方法在大多数基准上推动了最先进的函授学习。
translated by 谷歌翻译
In this paper, we propose an end-to-end framework that jointly learns keypoint detection, descriptor representation and cross-frame matching for the task of image-based 3D localization. Prior art has tackled each of these components individually, purportedly aiming to alleviate difficulties in effectively train a holistic network. We design a self-supervised image warping correspondence loss for both feature detection and matching, a weakly-supervised epipolar constraints loss on relative camera pose learning, and a directional matching scheme that detects key-point features in a source image and performs coarse-to-fine correspondence search on the target image. We leverage this framework to enforce cycle consistency in our matching module. In addition, we propose a new loss to robustly handle both definite inlier/outlier matches and less-certain matches. The integration of these learning mechanisms enables end-to-end training of a single network performing all three localization components. Bench-marking our approach on public data-sets, exemplifies how such an end-to-end framework is able to yield more accurate localization that out-performs both traditional methods as well as state-of-the-art weakly supervised methods.
translated by 谷歌翻译
We present ObjectMatch, a semantic and object-centric camera pose estimation for RGB-D SLAM pipelines. Modern camera pose estimators rely on direct correspondences of overlapping regions between frames; however, they cannot align camera frames with little or no overlap. In this work, we propose to leverage indirect correspondences obtained via semantic object identification. For instance, when an object is seen from the front in one frame and from the back in another frame, we can provide additional pose constraints through canonical object correspondences. We first propose a neural network to predict such correspondences on a per-pixel level, which we then combine in our energy formulation with state-of-the-art keypoint matching solved with a joint Gauss-Newton optimization. In a pairwise setting, our method improves registration recall of state-of-the-art feature matching from 77% to 87% overall and from 21% to 52% in pairs with 10% or less inter-frame overlap. In registering RGB-D sequences, our method outperforms cutting-edge SLAM baselines in challenging, low frame-rate scenarios, achieving more than 35% reduction in trajectory error in multiple scenes.
translated by 谷歌翻译
本地图像功能匹配,旨在识别图像对的识别和相应的相似区域,是计算机视觉中的重要概念。大多数现有的图像匹配方法遵循一对一的分配原则,并采用共同最近的邻居来确保跨图像之间本地特征之间的独特对应关系。但是,来自不同条件的图像可能会容纳大规模变化或观点多样性,以便一对一的分配可能在密集匹配中导致模棱两可或丢失的表示形式。在本文中,我们介绍了一种新颖的无探测器本地特征匹配方法Adamatcher,该方法首先通过轻巧的特征交互模块与密集的特征相关联,并估算了配对图像的可见面积,然后执行贴片级多到 - 一个分配可以预测匹配建议,并最终根据一对一的完善模块进行完善。广泛的实验表明,Adamatcher的表现优于固体基线,并在许多下游任务上实现最先进的结果。此外,多对一分配和一对一的完善模块可以用作其他匹配方法(例如Superglue)的改进网络,以进一步提高其性能。代码将在出版时提供。
translated by 谷歌翻译
现有方法以非可分子点检测关键点,因此它们不能直接通过背部传播优化关键点的位置。为解决此问题,我们呈现了一个可差异的关键点检测模块,其输出精确的子像素键点。然后提出了再分断损耗直接优化这些子像素键点,并且呈现了分散峰值损耗以获得准确的关键点正则化。我们还以子像素方式提取描述符,并通过稳定的神经输注误差丢失训练。此外,轻量化网络被设计用于关键点检测和描述符提取,其可以在商业GPU上以每秒95帧运行为95帧。在同性记估计,相机姿态估计和视觉(重新)定位任务中,所提出的方法通过最先进的方法实现了相同的性能,而大大减少了推理时间。
translated by 谷歌翻译
我们解决了一对图像之间找到密集的视觉对应关系的重要任务。由于各种因素,例如质地差,重复的模式,照明变化和运动模糊,这是一个具有挑战性的问题。与使用密集信号基础真相作为本地功能匹配培训的直接监督的方法相反,我们训练3DG-STFM:一种多模式匹配模型(教师),以在3D密集的对应性监督下执行深度一致性,并将知识转移到2D单峰匹配模型(学生)。教师和学生模型均由两个基于变压器的匹配模块组成,这些模块以粗略的方式获得密集的对应关系。教师模型指导学生模型学习RGB诱导的深度信息,以实现粗糙和精细分支的匹配目的。我们还在模型压缩任务上评估了3DG-STFM。据我们所知,3DG-STFM是第一种用于本地功能匹配任务的学生教师学习方法。该实验表明,我们的方法优于室内和室外摄像头姿势估计以及同型估计问题的最先进方法。代码可在以下网址获得:https://github.com/ryan-prime/3dg-stfm。
translated by 谷歌翻译
点云注册是许多应用程序(例如本地化,映射,跟踪和重建)的基本任务。成功的注册依赖于提取鲁棒和歧视性的几何特征。现有的基于学习的方法需要高计算能力来同时处理大量原始点。尽管这些方法取得了令人信服的结果,但由于高计算成本,它们很难在现实情况下应用。在本文中,我们介绍了一个框架,该框架使用图形注意网络有效地从经济上提取密集的特征,以进行点云匹配和注册(DFGAT)。 DFGAT的检测器负责在大型原始数据集中找到高度可靠的关键点。 DFGAT的描述符将这些关键点与邻居相结合,以提取不变的密度特征,以准备匹配。图形注意力网络使用了丰富点云之间关系的注意机制。最后,我们将其视为最佳运输问题,并使用Sinkhorn算法找到正匹配和负面匹配。我们对KITTI数据集进行了彻底的测试,并评估了该方法的有效性。结果表明,与其他最先进的方法相比,使用有效紧凑的关键点选择和描述可以实现最佳性能匹配指标,并达到99.88%注册的最高成功率。
translated by 谷歌翻译
在本文中,我们解决了估算图像之间尺度因子的问题。我们制定规模估计问题作为对尺度因素的概率分布的预测。我们设计了一种新的架构,ScaleNet,它利用扩张的卷积以及自我和互相关层来预测图像之间的比例。我们展示了具有估计尺度的整流图像导致各种任务和方法的显着性能改进。具体而言,我们展示了ScaleNet如何与稀疏的本地特征和密集的通信网络组合,以改善不同的基准和数据集中的相机姿势估计,3D重建或密集的几何匹配。我们对多项任务提供了广泛的评估,并分析了标准齿的计算开销。代码,评估协议和培训的型号在https://github.com/axelbarroso/scalenet上公开提供。
translated by 谷歌翻译
本地功能匹配是在子像素级别上的计算密集任务。尽管基于检测器的方法和特征描述符在低文本场景中遇到了困难,但具有顺序提取到匹配管道的基于CNN的方法无法使用编码器的匹配能力,并且倾向于覆盖用于匹配的解码器。相比之下,我们提出了一种新型的层次提取和匹配变压器,称为火柴场。在层次编码器的每个阶段,我们将自我注意事项与特征提取和特征匹配的交叉注意相结合,从而产生了人直觉提取和匹配方案。这种匹配感知的编码器释放了过载的解码器,并使该模型高效。此外,将自我交叉注意在分层体系结构中的多尺度特征结合起来,可以提高匹配的鲁棒性,尤其是在低文本室内场景或更少的室外培训数据中。得益于这样的策略,MatchFormer是效率,鲁棒性和精度的多赢解决方案。与以前的室内姿势估计中的最佳方法相比,我们的Lite MatchFormer只有45%的Gflops,但获得了 +1.3%的精度增益和41%的运行速度提升。大型火柴构造器以四个不同的基准达到最新的基准,包括室内姿势估计(SCANNET),室外姿势估计(Megadepth),同型估计和图像匹配(HPATCH)和视觉定位(INLOC)。
translated by 谷歌翻译
变换同步是从给定的一组相对运动中恢复绝对变换的问题。尽管有其有用,但由于嘈杂和异常相对运动的影响,问题仍然具有挑战性,以及模拟分析并抑制它们高保真的难度。在这项工作中,我们避免了手工强大的损失功能,并建议使用图形神经网络(GNN)来学习转换同步。与使用复杂的多阶段管道的先前作品不同,我们使用迭代方法,其中每个步骤由单个重量共享消息传递层组成,通过预测切线空间中的增量更新,从前一个迭代中改进绝对姿势。为了减少异常值的影响,在聚合之前将加权消息。我们的迭代方法减轻了对明确初始化步骤的需求,并使用身份初始姿势进行良好。虽然我们的方法很简单,但我们表明它通过SO(3)和SE(3)同步的实验来对现有的手工和学习的同步方法进行有利的。
translated by 谷歌翻译
在许多计算机视觉管道中,在图像之间建立一组稀疏的关键点相关性是一项基本任务。通常,这转化为一个计算昂贵的最近邻居搜索,必须将一个图像的每个键盘描述符与其他图像的所有描述符进行比较。为了降低匹配阶段的计算成本,我们提出了一个能够检测到每个图像处的互补关键集的深度提取网络。由于仅需要在不同图像上比较同一组中的描述符,因此匹配相计算复杂度随集合数量而降低。我们训练我们的网络以预测关键点并共同计算相应的描述符。特别是,为了学习互补的关键点集,我们引入了一种新颖的无监督损失,对不同集合之间的交叉点进行了惩罚。此外,我们提出了一种基于描述符的新型加权方案,旨在惩罚使用非歧视性描述符的关键点的检测。通过广泛的实验,我们表明,我们的功能提取网络仅在合成的扭曲图像和完全无监督的方式进行训练,以降低匹配的复杂性,在3D重建和重新定位任务上取得了竞争成果。
translated by 谷歌翻译