Camera Pose Estimation Research Articles

Leveraging 360° Camera in 3D Reconstruction: A Vision-Based Approach

In this paper, we present a novel vision-based approach for 3D reconstruction using a single 360° camera, aiming to offer a simplified and accessible solution for various consumer-oriented applications. Consumer-grade 360° cameras have gained significant popularity due to their affordability and ease of use. However, traditional methods for 3D reconstruction often require complex setups with multiple cameras or expensive hardware such as Light Detection and Ranging (LiDAR). Our approach addresses the challenges associated with 360° cameras by converting the distorted Equirectangular Projection (ERP) into four perspective views, allowing compatibility with deep learning models trained on undistorted perspective images. We leverage Visual Simultaneous Localization and Mapping (VSLAM) techniques for camera pose estimation and employ a standard 3D reconstruction pipeline for generating detailed 3D mesh representations of the indoor environment. Through experimental evaluation, we compare the performance of 360° cameras with traditional perspective cameras in 3D reconstruction and analyze the accuracy and performance of our vision-based approach. Our findings demonstrate the potential of using 360° cameras for constructing high-quality models and facilitating efficient data collection for 3D reconstructions, opening up new possibilities for various consumer-oriented applications in multiple fields.

A comparative study of pose estimation algorithms for visual navigation in autonomous robots

Autonomous navigation is a research field that gives mobile robots the capacity to perform various tasks without human assistance. Autonomous navigation based on visual sensors can be used in GPS denied environments. Vision-based navigation performs feature detection, matching, and pose estimation using camera images. This paper presents a new approach to autonomous navigation for mobile robots using a Color-based Image Segmentation and Centroid Detection algorithm instead of traditional feature detection algorithms. The algorithm intentionally matches features across images using known feature points and uses conventional techniques such as Epipolar Geometry and Perspective-N-Points algorithms for camera pose estimation. The study includes camera calibration to estimate intrinsic parameters and their physical unit conversion ensuring accurate measurements. Experimental datasets are used to analyze the performance of the Epipolar geometry, Perspective-3-Point, and Efficient-Perspective-n-Point based pose estimation algorithms. To enhance accuracy, the P3P algorithm is modified to consider combinations of image points for pose estimation. The paper concludes with a comparative analysis between the original P3P algorithm and the modified version, providing valuable insights into their respective performances. Overall, the paper aims to provide a comparison of different pose estimation algorithms used for visual navigation. Keywords: pose estimation, visual navigation, camera calibration, perspective-n-point, efficient pnp, epipolar geometry Abbreviations PnP, perspective-n-point; P3P, perspective-3-point; EPnP, efficient perspective-n-point; SLAM, simultaneous localization and mapping; VO, visual odometry; GPS, global positioning system; SURF, speeded up robust features; SIFT, scale-invariant feature transform; EKF, extended kalman filter; RGB, red-green-blue; HSV, hue- saturation-value; CNN, convolutional neural network

TransCNNLoc: End-to-end pixel-level learning for 2D-to-3D pose estimation in dynamic indoor scenes

Accurate localization in GPS-denied environments has always been a core issue in computer vision and robotics research. In indoor environments, vision-based localization methods are susceptible to changes in lighting conditions, viewing angles, and environmental factors, resulting in localization failures or limited generalization capabilities. In this paper, we propose the TransCNNLoc framework, which consists of an encoding–decoding network designed to learn more robust image features for camera pose estimation. In the image feature encoding stage, CNN and Swin Transformer are integrated to construct the image feature encoding module, enabling the network to fully extract global context and local features from images. In the decoding stage, multi-level image features are decoded through cross-layer connections while computing per-pixel feature weight maps. To enhance the framework’s robustness to dynamic objects, a dynamic object recognition network is introduced to optimize the feature weights. Finally, a multi-level iterative optimization from coarse to fine levels is performed to recover six degrees of freedom camera pose. Experiments were conducted on the publicly available 7scenes dataset as well as a dataset collected under changing lighting conditions and dynamic scenes for accuracy validation and analysis. The experimental results demonstrate that the proposed TransCNNLoc framework exhibits superior adaptability to dynamic scenes and lighting changes. In the context of static environments within publicly available datasets, the localization technique introduced in this study attains a maximal precision of up to 5 centimeters, consistently achieving superior outcomes across a majority of the scenarios. Under the conditions of dynamic scenes and fluctuating illumination, this approach demonstrates an enhanced precision capability, reaching up to 3 centimeters. This represents a substantial refinement from the decimeter scale to a centimeter scale in precision, marking a significant advancement over the existing state-of-the-art (SOTA) algorithms. The open-source repository for the method proposed in this paper can be found at the following URL: github.com/Geelooo/TransCNNloc.

A critical analysis of image-based camera pose estimation techniques

Camera, and associated with its objects within the field of view, localization could benefit many computer vision fields, such as autonomous driving, robot navigation, and augmented reality (AR). After decades of progress, camera localization, also called camera pose estimation could compute the 6DoF pose of objects for a camera in a given image, with respect to different images in a sequence or formats. Structure feature-based localization methods have achieved great success when integrated with image matching or with a coordinate regression stage. Absolute and relative pose regression methods using transfer learning can support end-to-end localization to directly regress a camera pose but achieve a less accurate performance. Despite the rapid development of multiple branches in this area, a comprehensive, in-depth and comparative analysis is lacking to summarize, classify and compare, structure feature-based and regression-based camera localization methods. Existing surveys either focus on larger SLAM (Simultaneous Localization and Mapping) systems or on only part of the camera localization method, lack detailed comparisons and descriptions of the methods or datasets used, neural network designs such as loss designs, and input formats, etc. In this survey, we first introduce specific application areas and the evaluation metrics for camera localization pose according to different sub-tasks (learning-based 2D-2D task, 2D-3D task, and 3D-3D task). Then, we review common methods for structure feature-based camera pose estimation approaches, absolute pose regression and relative pose regression approaches by critically modelling the methods to inspire further improvements in their algorithms such as loss functions, and neural network structures. Furthermore, we summarize what are the popular datasets used for camera localization and compare the quantitative and qualitative results of these methods with detailed performance metrics. Finally, we discuss future research possibilities and applications.

A robust direct linear transformation for camera pose estimation using points

Camera pose estimation from 3D points and their 2D projections, known as the perspective-n-point (PnP) problem, is a fundamental task in computer vision. In this paper, we propose a robust direct linear transformation method for the PnP problem. The novelty lies in that a plane constraint based on the pinhole camera model is introduced, and an over-constrained linear equation system is obtained by merging the linear form of both the measured point correspondences and the plane constraint. As a result, our method successfully reduces the minimal number of point correspondences required by the linear solver to 4, and yields a unique solution for 4-point, 5-point, and n-point pose estimation. Experiment results, using both synthetic and real data, show that our method is substantially faster, and offers the accuracy and precision comparable with that of state-of-the-art methods.

Robust RGB: D-SLAM in highly dynamic environments based on probability observations and clustering optimization

Visual simultaneous localization and mapping (SLAM) is the underlying support of unmanned systems. Currently, most visual SLAM methods are based on the static environment assumption so that dynamic objects in the camera’s field of view will seriously disrupt its working performance. In view of this, an RGB-D SLAM approach based on probability observations and clustering optimization for highly dynamic environments is proposed, which can effectively eliminate the influence of dynamic objects and accurately estimate the ego-motion of an RGB-D camera. The method contains a dual static map point detection strategy, which is carried out simultaneously in the current and previous frames. First, to enhance tracking robustness in highly dynamic environments, the probabilities of map points being static, calculated by both reprojection deviation and intensity deviation, are used to weight the cost function for pose estimation. Meanwhile, by taking the previous frames as a reference, a static velocity probability based on sparse scene flow is acquired to preliminarily recognize static map points and further improve the tracking accuracy. Then, an improved map point optimization strategy based on K-means clustering is designed, which effectively takes advantage of the clustering algorithm to refine the static map point labels while alleviating its stubborn problem. Finally, the experimental results on the TUM dataset and real scenes compared with the state-of-the-art visual SLAM methods illustrate that the proposed method achieves an extremely robust and accurate performance for estimating camera pose in highly dynamic environments.

Fiducial Objects: Custom Design and Evaluation.

Camera pose estimation is vital in fields like robotics, medical imaging, and augmented reality. Fiducial markers, specifically ArUco and Apriltag, are preferred for their efficiency. However, their accuracy and viewing angle are limited when used as single markers. Custom fiducial objects have been developed to address these limitations by attaching markers to 3D objects, enhancing visibility from multiple viewpoints and improving precision. Existing methods mainly use square markers on non-square object faces, leading to inefficient space use. This paper introduces a novel approach for creating fiducial objects with custom-shaped markers that optimize face coverage, enhancing space utilization and marker detectability at greater distances. Furthermore, we present a technique for the precise configuration estimation of these objects using multiviewpoint images. We provide the research community with our code, tutorials, and an application to facilitate the building and calibration of these objects. Our empirical analysis assesses the effectiveness of various fiducial objects for pose estimation across different conditions, such as noise levels, blur, and scale variations. The results suggest that our customized markers significantly outperform traditional square markers, marking a positive advancement in fiducial marker-based pose estimation methods.

NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction.

This paper studies the challenging two-view 3D reconstruction problem in a rigorous sparse-view configuration, which is suffering from insufficient correspondences in the input image pairs for camera pose estimation. We present a novel Neural One-PlanE RANSAC framework (termed NOPE-SAC in short) that exerts excellent capability of neural networks to learn one-plane pose hypotheses from 3D plane correspondences. Building on the top of a Siamese network for plane detection, our NOPE-SAC first generates putative plane correspondences with a coarse initial pose. It then feeds the learned 3D plane correspondences into shared MLPs to estimate the one-plane camera pose hypotheses, which are subsequently reweighed in a RANSAC manner to obtain the final camera pose. Because the neural one-plane pose minimizes the number of plane correspondences for adaptive pose hypotheses generation, it enables stable pose voting and reliable pose refinement with a few of plane correspondences for the sparse-view inputs. In the experiments, we demonstrate that our NOPE-SAC significantly improves the camera pose estimation for the two-view inputs with severe viewpoint changes, setting several new state-of-the-art performances on two challenging benchmarks, i.e., MatterPort3D and ScanNet, for sparse-view 3D reconstruction. The source code is released at https://github.com/IceTTTb/NopeSAC for reproducible research.

Learning Probabilistic Coordinate Fields for Robust Correspondences.

We introduce Probabilistic Coordinate Fields (PCFs), a novel geometric-invariant coordinate representation for image correspondence problems. In contrast to standard Cartesian coordinates, PCFs encode coordinates in correspondence-specific barycentric coordinate systems (BCS) with affine invariance. To know when and where to trust the encoded coordinates, we implement PCFs in a probabilistic network termed PCF-Net, which parameterizes the distribution of coordinate fields as Gaussian mixture models. By jointly optimizing coordinate fields and their confidence conditioned on dense flows, PCF-Net can work with various feature descriptors when quantifying the reliability of PCFs by confidence maps. An interesting observation of this work is that the learned confidence map converges to geometrically coherent and semantically consistent regions, which facilitates robust coordinate representation. By delivering the confident coordinates to keypoint/feature descriptors, we show that PCF-Net can be used as a plug-in to existing correspondence-dependent approaches. Extensive experiments on both indoor and outdoor datasets suggest that accurate geometric invariant coordinates help to achieve the state of the art in several correspondence problems, such as sparse feature matching, dense image registration, camera pose estimation, and consistency filtering. Further, the interpretable confidence map predicted by PCF-Net can also be leveraged to other novel applications from texture transfer to multi-homography classification.

DIG-SLAM: an accurate RGB-D SLAM based on instance segmentation and geometric clustering for dynamic indoor scenes

Simultaneous localization and mapping (SLAM) has emerged as a critical technology enabling robots to navigate in unknown environments, drawing extensive attention within the robotics research community. However, traditional visual SLAM ignores the presence of dynamic objects in indoor scenes, and dynamic point features of dynamic objects can lead to incorrect data correlation, making the traditional visual SLAM is difficult to accurately estimate the camera’s pose when the objects in the scenes are moving. Using only point features cannot fully extract geometric information in dynamic indoor scenes, reducing the system’s robustness. To solve this problem, we develop a RGB-D SLAM system called DIG-SLAM. Firstly, the objects’ contour regions are extracted using the YOLOv7 instance segmentation method, serving as a prerequisite for determining dynamic objects and constructing a semantic information map. Meanwhile, the line features are extracted using the line segment detector algorithm, and the redundant line features are optimized via K-means clustering. Secondly, moving consistency checks combined with instance partitioning determine dynamic regions, and the point and line features of the dynamic regions are removed. Finally, the combination of static line features and point features optimizes the camera pose. Meanwhile, a static semantic octree map is created to provide richer and higher-level scene understanding and perception capabilities for robots or autonomous systems. The experimental results on the Technische Universität München dataset show that the average absolute trajectory error of the developed DIG-SLAM is reduced by 28.68% compared with the dynamic semantic SLAM. Compared with other dynamic SLAM methods, the proposed system shows better camera pose estimation accuracy and system’s robustness in dynamic indoor environments and better map building in real indoor scenes.

IMPROVING CAMERA POSE ESTIMATION USING SWARM PARTICLE ALGORITHMS

Abstract. Most computer vision and photogrammetry applications rely on accurately estimating the camera pose, such as visual navigation, motion tracking, stereo photogrammetry, and structure from motion. The Essential matrix is a well-known model in computer vision that provides information about the relative orientation between two images, including the rotation and translation, for calibrated cameras with a known camera matrix. To estimate the Essential matrix, the camera calibration matrices, which include focal length and principal point location must be known, and the estimation process typically requires at least five matching points and the use of robust algorithms, such as RANSAC to fit a model to the data as a robust estimator. From the usually large number of matched points, choosing five points, the Essential matrix can be determined based on a simple solution, which could be good or bad. Obtaining a globally optimal and accurate camera pose estimation, however, requires additional steps, such as using evolutionary algorithms (EA) or swarm algorithms (SA), to prevent getting trapped in local optima by searching for solutions within a potentially huge solution space.This paper aims to introduce an improved method for estimating the Essential matrix using swarm particle algorithms that are known to efficiently solve complex problems. Various optimization techniques, including EAs and SAs, such as Particle Swarm Optimization (PSO), Gray Wolf Optimization (GWO), Improved Gray Wolf Optimization (IGWO), Genetic Algorithm (GA), Salp Swarm Algorithm (SSA) and Whale Optimization Algorithm (WOA), are explored to obtain the global minimum of the reprojection error for the five-point Essential matrix estimation based on using symmetric geometric error cost function. The experimental results on a dataset with known camera orientation demonstrate that the IGWO method has achieved the best score compared to other techniques and significantly speeds up the camera pose estimation for larger number of point pairs in contrast to traditional methods that use the collinearity equations in an iterative adjustment.

A Novel Visual SLAM Based on Multiple Deep Neural Networks

The current visual simultaneous localization and mapping (SLAM) systems require the use of matched feature point pairs to estimate camera pose and construct environmental maps. Therefore, they suffer from poor performance of the visual feature matchers. To address this problem, a visual SLAM using deep feature matcher is proposed, which is mainly composed of three parallel threads: Visual Odometry, Backend Optimizer and LoopClosing. In the Visual Odometry, the deep feature extractor with convolutional neural networks is utilized for extracting feature points in each image frame. Then, the deep feature matcher is used for obtaining the corresponding feature landmark pairs. Afterwards, a fusion method based on the last and the reference frame is proposed for camera pose estimation. The Backend Optimizer is designed to execute local bundle adjustment for a part of camera poses and landmarks (map points). While LoopClosing, consisting of a lightweight deep loop closure detector and the same matcher as the one used in Visual Odometry is utilized for loop correction based on pose graph. The proposed system has been tested extensively on most of benchmark KITTI odometry dataset. The experimental results show that our system yields better performance than the existing visual SLAM systems. It can not only run in real-time at a speed of 0.08 s per frame, but also reduce estimation error by at least 0.1 m.

Improving sparse graph attention for feature matching by informative keypoints exploration

Feature matching refers to building correct point correspondences from two-view images. Typical methods create coarse matches merely based on the similarity of local descriptors, then additionally use geometrical constraints or coherence to get a clean match set. However, this indirect paradigm would be strictly limited by the pre-matching results. This can be alleviated by a GNN-based matching network that constructs correct correspondences directly from feature positions and descriptions. Attentional pooling is utilized to reduce the high computational complexity and memory usage by sparsing the graph attention. In this paper, we propose an enhanced sparse GNN, namely KeyGNN, for fast feature matching, by designing Guided Attentional Pooling to emphasize the informative cues in GNN layers. Specifically, we propose Informative Keypoints Exploration Module and Guided Sparse Module to respectively extract information-rich points and use them to guide the attentional pooling for better information preservation. This process is constrained by the proposed Structural Importance Ranking Loss and Descriptor Distribution Loss, that ensure the structural information can be correctly extracted and the generated feature vectors be well distributed in the deep space. Unlike existing techniques, our method can focus and preserve more on the main information in the sparse GNN stage, thus avoiding information loss and enhancing the accuracy. Extensive experiments on large and public datasets reveal that our method can obtain better performance than the state-of-the-arts in the tasks of camera pose estimation, fundamental matrix estimation, and visual localization. The runtime and memory test shows that our network takes low computational and memory usage, which is friendly to real-time vision tasks.

Synthetic image data generation using BIM and computer graphics for building scene understanding

Vision-based building scene understanding (BSU) is essential to many applications such as indoor navigation and 3D reconstruction. Deep learning excels in various BSU tasks but its training relies heavily on large-scale datasets, which are often burdensome and costly to obtain. This study proposes a universal and automated approach to generate synthetic building images with comprehensive annotations that support twelve BSU tasks, including camera pose estimation, scene recognition, depth estimation, 2D/3D object and object part detection, object and material semantic segmentation, object and object part instance segmentation, and panoptic segmentation. This approach captures and renders perspective views of indoor BIM model scenes to generate photorealistic images. Required annotations are computed by a ray tracing-based algorithm accelerated by two-tier axis-aligned bounding box tree indexing. The approach was validated by efficiently producing annotated synthetic images from various BIM models, and preliminary experiments demonstrated the promising efficacy of the synthetic images for deep learning model training.

Single-Point Least Square Matching Embedded Method for Improving Visual SLAM

Visual simultaneous location and mapping (VSLAM) has been widely used today, but for some tough cases with insufficient feature points (such as weak texture and motion blur), it is still an ongoing challenge to further boost the corresponding robustness and accuracy. In this paper, to address the problem of inadequate feature points, for conventional visual SLAM, we improve the original feature matching mechanism by providing more correspondences with higher position precision. Firstly, based on the original feature matching results in the map initialization stage, a single-point least square matching (LSM) which iteratively refines position of the matching points by considering geometric and photometric consistency, is presented to improve the map initialization result. Secondly, to improve the tracking performance, given the motion model, the single-point LSM is again used to yield new correspondences from the unsuccessfully matched features of original matching mechanism between current frame and previous frame in the tracking thread, and these extra correspondences participate in and boost the subsequent pose optimization. Lastly, for newly inserted keyframe, we focus on identifying the corresponding 3D map points’ reprojections on relevant local neighbor keyframes, these reprojections are added in the local bundle adjustment (BA) optimization for further improving the estimation of camera pose and local map. The popular VSLAM package, ORB-SLAM2, is used to demonstrate the efficacy of the proposed improvements. An ablation study on accuracy and tracking stability on public datasets are reported, furthermore, the comparisons with several state of the arts (namely, VINS-Mono, ORB-SLAM3, DSO, PL-SLAM) are investigated. The experimental results show that our approach can improve accuracy in weak texture scenes and motion blur cases, reduce the number of tracking loss and improve tracking robustness.

Two-view correspondence learning using graph neural network with reciprocal neighbor attention

Recent advances in two-view correspondence learning consider aggregating local contextual information from k-nearest neighbors by exploring local geometric extractors using convolution, graph or self-attention. However, there is no guarantee that the extracted local context is conducive to correspondence pruning, since there are typically over 90% outliers in the putative set which would inevitably result in contaminated neighbors and hence contaminated local context. To address this issue, in this paper, we propose the RNA-GNN, an attentional graph neural network (GNN) architecture, which can explicitly model interactions among relevant neighboring correspondences. Specifically, a reciprocal neighbor attention (RNA) module is designed to operate sparse attention on relevant neighbors only rather than all neighbors, mitigating the interference of irrelevant and redundant connectivity, and learning more compact and robust representation. In addition, considering that seeking reliable correspondences requires both local and global context, we introduce a context-aware attention module to extract global and channel-wise context by means of global weighted average pooling with weights that are estimated within the network, excluding outliers from this pooling. Extensive experiments on publicly available datasets demonstrate that RNA-GNN substantially advances current state-of-the-arts on camera pose estimation, homography estimation, and remote sensing image registration. Our code is publicly available at https://github.com/ZizhuoLi/RNA-GNN.

Context-enhanced motion coherence modeling for global outlier rejection

Feature matching is an essential step in a wide range of photogrammetry and computer vision tasks but limited by the ambiguities of local descriptors. Hence, numerous false feature matches (outliers) will inevitably be generated, especially in complex scenarios. Motion coherence can establish the statistical relationships among sparse motions to remove outliers, assuming that the true matches are coherent, and the false matches are randomly scattered. However, existing methods model motion coherence either in a local spatial context or without considering rich matching priors, thereby leading to numerous matching failures when outlier rates are high. In this study, we propose a context-enhanced motion coherence modeling (CoMo) method to distinguish consistent correct motions from erroneous matches for robust outlier rejection. The CoMo method deploys a consistency-aware motion descriptor to encode the consistency-related matching priors of feature matches as a high-dimensional representation, which can provide a rich context for differentiating heterogeneous motions. Based on this discriminative descriptor, we further introduce deformable affine transformation (DAT) as a proxy for motion and fit the coherent motions from the candidate matches with a globally smooth function under the truncated least squares estimation framework. Extensive experiments on multiple large datasets (including the Image Matching Challenge at CVPR 2020) demonstrate that the CoMo method can effectively model motion coherence from noisy candidate matches and outperform other state-of-the-art methods in outlier rejection and relative camera pose estimation. The code is available at https://github.com/geovsion/CoMo.

Feature Point Tracking Method for Visual SLAM Based on Multi-Condition Constraints in Light Changing Environment

In scenes where there are lighting changes, localization may fail for visual SLAM due to feature point tracking failure. Thus, a feature point tracking method based on multi-condition constraints is proposed for visual SLAM. The proposed method tracks the feature points of optical flow from aspects such as the overall motion position of feature points, descriptor grayscale information, and spatial geometric constraints. First, to solve the problem of feature point mismatch in complex environments, we propose a feature point mismatch removal method that combines optical flow, descriptor, and RANSAC. We eliminate incorrect feature point matches layer by layer through these constraints. The uniformity of feature point distribution in the image can then affect the accuracy of camera pose estimation, and different scenes can also affect the difficulty of feature point extraction. In order to balance the quality and uniformity of the extracted feature points, we propose an adaptive mask homogenization method that adaptively adjusts the mask radius according to the quality of feature points. Experiments conducted on the EuRoC dataset show that the proposed method which integrates the improved feature point mismatch removal method and mask homogenization method into feature point tracking, exhibits robustness and accuracy under various interferences such as lighting changes, image blurring, and unclear textures. Compared to the RANSAC method, we reduce the location error by about 85% using the EuRoC dataset.

Perspective-1-Ellipsoid: Formulation, Analysis and Solutions of the Camera Pose Estimation Problem from One Ellipse-Ellipsoid Correspondence

Perspective-1-Ellipsoid: Formulation, Analysis and Solutions of the Camera Pose Estimation Problem from One Ellipse-Ellipsoid Correspondence

Unsupervised Monocular Depth and Camera Pose Estimation with Multiple Masks and Geometric Consistency Constraints.

This paper presents a novel unsupervised learning framework for estimating scene depth and camera pose from video sequences, fundamental to many high-level tasks such as 3D reconstruction, visual navigation, and augmented reality. Although existing unsupervised methods have achieved promising results, their performance suffers in challenging scenes such as those with dynamic objects and occluded regions. As a result, multiple mask technologies and geometric consistency constraints are adopted in this research to mitigate their negative impacts. Firstly, multiple mask technologies are used to identify numerous outliers in the scene, which are excluded from the loss computation. In addition, the identified outliers are employed as a supervised signal to train a mask estimation network. The estimated mask is then utilized to preprocess the input to the pose estimation network, mitigating the potential adverse effects of challenging scenes on pose estimation. Furthermore, we propose geometric consistency constraints to reduce the sensitivity of illumination changes, which act as additional supervised signals to train the network. Experimental results on the KITTI dataset demonstrate that our proposed strategies can effectively enhance the model's performance, outperforming other unsupervised methods.