We address the problem of depth and ego-motion estimation from image sequences. Recent advances in the domain propose to train a deep learning model for both tasks using image reconstruction in a self-supervised manner. We revise the assumptions and the limitations of the current approaches and propose two improvements to boost the performance of the depth and ego-motion estimation. We first use Lie group properties to enforce the geometric consistency between images in the sequence and their reconstructions. We then propose a mechanism to pay an attention to image regions where the image reconstruction get corrupted. We show how to integrate the attention mechanism in the form of attention gates in the pipeline and use attention coefficients as a mask. We evaluate the new architecture on the KITTI datasets and compare it to the previous techniques. We show that our approach improves the state-of-the-art results for ego-motion estimation and achieve comparable results for depth estimation.
Forecasting motion of a specific target object is a common problem for surgical interventions, e.g. for localization of a target region, guidance for surgical interventions, or motion compensation. Optical coherence tomography (OCT) is an imaging modality with a high spatial and temporal resolution. Recently, deep learning methods have shown promising performance for OCT-based motion estimation based on two volumetric images. We extend this approach and investigate whether using a time series of volumes enables motion forecasting. We propose 4D spatio-temporal deep learning for end-to-end motion forecasting and estimation using a stream of OCT volumes. We design and evaluate five different 3D and 4D deep learning methods using a tissue data set. Our best performing 4D method achieves motion forecasting with an overall average correlation coefficient of 97.41%, while also improving motion estimation performance by a factor of 2.5 compared to a previous 3D approach.
Purpose. Localizing structures and estimating the motion of a specific target region are common problems for navigation during surgical interventions. Optical coherence tomography (OCT) is an imaging modality with a high spatial and temporal resolution that has been used for intraoperative imaging and also for motion estimation, for example, in the context of ophthalmic surgery or cochleostomy. Recently, motion estimation between a template and a moving OCT image has been studied with deep learning methods to overcome the shortcomings of conventional, feature-based methods. Methods. We investigate whether using a temporal stream of OCT image volumes can improve deep learning-based motion estimation performance. For this purpose, we design and evaluate several 3D and 4D deep learning methods and we propose a new deep learning approach. Also, we propose a temporal regularization strategy at the model output. Results. Using a tissue dataset without additional markers, our deep learning methods using 4D data outperform previous approaches. The best performing 4D architecture achieves an correlation coefficient (aCC) of 98.58% compared to 85.0% of a previous 3D deep learning method. Also, our temporal regularization strategy at the output further improves 4D model performance to an aCC of 99.06%. In particular, our 4D method works well for larger motion and is robust towards image rotations and motion distortions. Conclusions. We propose 4D spatio-temporal deep learning for OCT-based motion estimation. On a tissue dataset, we find that using 4D information for the model input improves performance while maintaining reasonable inference times. Our regularization strategy demonstrates that additional temporal information is also beneficial at the model output.
Extreme image or video completion, where, for instance, we only retain 1% of pixels in random locations, allows for very cheap sampling in terms of the required pre-processing. The consequence is, however, a reconstruction that is challenging for humans and inpainting algorithms alike. We propose an extension of a state-of-the-art extreme image completion algorithm to extreme video completion. We analyze a color-motion estimation approach based on color KL-divergence that is suitable for extremely sparse scenarios. Our algorithm leverages the estimate to adapt between its spatial and temporal filtering when reconstructing the sparse randomly-sampled video. We validate our results on 50 publicly-available videos using reconstruction PSNR and mean opinion scores.
Akin to many subareas of computer vision, the recent advances in deep learning have also significantly influenced the literature on optical flow. Previously, the literature had been dominated by classical energy-based models, which formulate optical flow estimation as an energy minimization problem. However, as the practical benefits of Convolutional Neural Networks (CNNs) over conventional methods have become apparent in numerous areas of computer vision and beyond, they have also seen increased adoption in the context of motion estimation to the point where the current state of the art in terms of accuracy is set by CNN approaches. We first review this transition as well as the developments from early work to the current state of CNNs for optical flow estimation. Alongside, we discuss some of their technical details and compare them to recapitulate which technical contribution led to the most significant accuracy improvements. Then we provide an overview of the various optical flow approaches introduced in the deep learning age, including those based on alternative learning paradigms (e.g., unsupervised and semi-supervised methods) as well as the extension to the multi-frame case, which is able to yield further accuracy improvements.
Video processing solutions for motion analysis are key tasks in many computer vision applications, ranging from human activity recognition to object detection. In particular, speed estimation algorithms may be relevant in contexts such as street monitoring and environment surveillance. In most realistic scenarios, the projection of a framed object of interest onto the image plane is likely to be affected by dynamic changes mainly related to perspectival transformations or periodic behaviours. Therefore, advanced speed estimation techniques need to rely on robust algorithms for object detection that are able to deal with potential geometrical modifications. The proposed method is composed of a sequence of pre-processing operations, that aim to reduce or neglect perspetival effects affecting the objects of interest, followed by the estimation phase based on the Maximum Likelihood (ML) principle, where the speed of the foreground objects is estimated. The ML estimation method represents, indeed, a consolidated statistical tool that may be exploited to obtain reliable results. The performance of the proposed algorithm is evaluated on a set of real video recordings and compared with a block-matching motion estimation algorithm. The obtained results indicate that the proposed method shows good and robust performance.
In this paper we consider a collection of relative pose problems which arise naturally in applications for visual indoor UAV navigation. We focus on cases where additional information from an onboard IMU is available and thus provides a partial extrinsic calibration through the gravitational vector. The solvers are designed for a partially calibrated camera, for a variety of realistic indoor scenarios, which makes it possible to navigate using images of the ground floor. Current state-of-the-art solvers use more general assumptions, such as using arbitrary planar structures; however, these solvers do not yield adequate reconstructions for real scenes, nor do they perform fast enough to be incorporated in real-time systems. We show that the proposed solvers enjoy better numerical stability, are faster, and require fewer point correspondences, compared to state-of-the-art solvers. These properties are vital components for robust navigation in real-time systems, and we demonstrate on both synthetic and real data that our method outperforms other methods, and yields superior motion estimation.
Dynamic environments are challenging for visual SLAM since the moving objects occlude the static environment features and lead to wrong camera motion estimation. In this paper, we present a novel dense RGB-D SLAM solution that simultaneously accomplishes the dynamic/static segmentation and camera ego-motion estimation as well as the static background reconstructions. Our novelty is using optical flow residuals to highlight the dynamic semantics in the RGB-D point clouds and provide more accurate and efficient dynamic/static segmentation for camera tracking and background reconstruction. The dense reconstruction results on public datasets and real dynamic scenes indicate that the proposed approach achieved accurate and efficient performances in both dynamic and static environments compared to state-of-the-art approaches.
Existing video super-resolution (SR) algorithms usually assume that the blur kernels in the degradation process are known and do not model the blur kernels in the restoration. However, this assumption does not hold for video SR and usually leads to over-smoothed super-resolved images. In this paper, we propose a deep convolutional neural network (CNN) model to solve video SR by a blur kernel modeling approach. The proposed deep CNN model consists of motion blur estimation, motion estimation, and latent image restoration modules. The motion blur estimation module is used to provide reliable blur kernels. With the estimated blur kernel, we develop an image deconvolution method based on the image formation model of video SR to generate intermediate latent images so that some sharp image contents can be restored well. However, the generated intermediate latent images may contain artifacts. To generate high-quality images, we use the motion estimation module to explore the information from adjacent frames, where the motion estimation can constrain the deep CNN model for better image restoration. We show that the proposed algorithm is able to generate clearer images with finer structural details. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods.
Motion estimation of cardiac MRI videos is crucial for the evaluation of human heart anatomy and function. Recent researches show promising results with deep learning-based methods. In clinical deployment, however, they suffer dramatic performance drops due to mismatched distributions between training and testing datasets, commonly encountered in the clinical environment. On the other hand, it is arguably impossible to collect all representative datasets and to train a universal tracker before deployment. In this context, we proposed a novel fast online adaptive learning (FOAL) framework: an online gradient descent based optimizer that is optimized by a meta-learner. The meta-learner enables the online optimizer to perform a fast and robust adaptation. We evaluated our method through extensive experiments on two public clinical datasets. The results showed the superior performance of FOAL in accuracy compared to the offline-trained tracking method. On average, the FOAL took only $0.4$ second per video for online optimization.
Unsupervised learning of depth and ego-motion from unlabelled monocular videos has recently drawn great attention, which avoids the use of expensive ground truth in the supervised one. It achieves this by using the photometric errors between the target view and the synthesized views from its adjacent source views as the loss. Despite significant progress, the learning still suffers from occlusion and scene dynamics. This paper shows that carefully manipulating photometric errors can tackle these difficulties better. The primary improvement is achieved by a statistical technique that can mask out the invisible or nonstationary pixels in the photometric error map and thus prevents misleading the networks. With this outlier masking approach, the depth of objects moving in the opposite direction to the camera can be estimated more accurately. To the best of our knowledge, such scenarios have not been seriously considered in the previous works, even though they pose a higher risk in applications like autonomous driving. We also propose an efficient weighted multi-scale scheme to reduce the artifacts in the predicted depth maps. Extensive experiments on the KITTI dataset show the effectiveness of the proposed approaches. The overall system achieves state-of-theart performance on both depth and ego-motion estimation.
Autonomous navigation emerges from both motion and local visual perception in real-world environments. However, most successful robotic motion estimation methods (e.g. VO, SLAM, SfM) and vision systems (e.g. CNN, visual place recognition-VPR) are often separately used for mapping and localization tasks. Conversely, recent reinforcement learning (RL) based methods for visual navigation rely on the quality of GPS data reception, which may not be reliable when directly using it as ground truth across multiple, month-spaced traversals in large environments. In this paper, we propose a novel motion and visual perception approach, dubbed MVP, that unifies these two sensor modalities for large-scale, target-driven navigation tasks. Our MVP-based method can learn faster, and is more accurate and robust to both extreme environmental changes and poor GPS data than corresponding vision-only navigation methods. MVP temporally incorporates compact image representations, obtained using VPR, with optimized motion estimation data, including but not limited to those from VO or optimized radar odometry (RO), to efficiently learn self-supervised navigation policies via RL. We evaluate our method on two large real-world datasets, Oxford Robotcar and Nordland Railway, over a range of weather (e.g. overcast, night, snow, sun, rain, clouds) and seasonal (e.g. winter, spring, fall, summer) conditions using the new CityLearn framework; an interactive environment for efficiently training navigation agents. Our experimental results, on traversals of the Oxford RobotCar dataset with no GPS data, show that MVP can achieve 53% and 93% navigation success rate using VO and RO, respectively, compared to 7% for a vision-only method. We additionally report a trade-off between the RL success rate and the motion estimation precision.
Calibration of wide field-of-view cameras is a fundamental step for numerous visual media production applications, such as 3D reconstruction, image undistortion, augmented reality and camera motion estimation. However, existing calibration methods require multiple images of a calibration pattern (typically a checkerboard), assume the presence of lines, require manual interaction and/or need an image sequence. In contrast, we present a novel fully automatic deep learning-based approach that overcomes all these limitations and works with a single image of general scenes. Our approach builds upon the recent developments in deep Convolutional Neural Networks (CNN): our network automatically estimates the intrinsic parameters of the camera (focal length and distortion parameter) from a single input image. In order to train the CNN, we leverage the great amount of omnidirectional images available on the Internet to automatically generate a large-scale dataset composed of millions of wide field-of-view images with ground truth intrinsic parameters. Experiments successfully demonstrated the quality of our results, both quantitatively and qualitatively.
In autonomous driving, monocular sequences contain lots of information. Monocular depth estimation, camera ego-motion estimation and optical flow estimation in consecutive frames are high-profile concerns recently. By analyzing tasks above, pixels in the middle frame are modeled into three parts: the rigid region, the non-rigid region, and the occluded region. In joint unsupervised training of depth and pose, we can segment the occluded region explicitly. The occlusion information is used in unsupervised learning of depth, pose and optical flow, as the image reconstructed by depth-pose and optical flow will be invalid in occluded regions. A less-than-mean mask is designed to further exclude the mismatched pixels interfered with by motion or illumination change in the training of depth and pose networks. This method is also used to exclude some trivial mismatched pixels in the training of the optical flow network. Maximum normalization is proposed for depth smoothness term to restrain depth degradation in textureless regions. In the occluded region, as depth and camera motion can provide more reliable motion estimation, they can be used to instruct unsupervised learning of optical flow. Our experiments in KITTI dataset demonstrate that the model based on three regions, full and explicit segmentation of the occlusion region, the rigid region, and the non-rigid region with corresponding unsupervised losses can improve performance on three tasks significantly. The source code is available at: https://github.com/guangmingw/DOPlearning.
We address the problem of joint optical flow and camera motion estimation in rigid scenes by incorporating geometric constraints into an unsupervised deep learning framework. Unlike existing approaches which rely on brightness constancy and local smoothness for optical flow estimation, we exploit the global relationship between optical flow and camera motion using epipolar geometry. In particular, we formulate the prediction of optical flow and camera motion as a bi-level optimization problem, consisting of an upper-level problem to estimate the flow that conforms to the predicted camera motion, and a lower-level problem to estimate the camera motion given the predicted optical flow. We use implicit differentiation to enable back-propagation through the lower-level geometric optimization layer independent of its implementation, allowing end-to-end training of the network. With globally-enforced geometric constraints, we are able to improve the quality of the estimated optical flow in challenging scenarios and obtain better camera motion estimates compared to other unsupervised learning methods.
Contrast maximisation estimates the motion captured in an event stream by maximising the sharpness of the motion compensated event image. To carry out contrast maximisation, many previous works employ iterative optimisation algorithms, such as conjugate gradient, which require good initialisation to avoid converging to bad local minima. To alleviate this weakness, we propose a new globally optimal event-based motion estimation algorithm. Based on branch-and-bound (BnB), our method solves rotational (3DoF) motion estimation on event streams, which supports practical applications such as video stabilisation and attitude estimation. Underpinning our method are novel bounding functions for contrast maximisation, whose theoretical validity is rigorously established. We show concrete examples from public datasets where globally optimal solutions are vital to the success of contrast maximisation. Despite its exact nature, our algorithm is currently able to process a 50,000 event input in 300 seconds (a locally optimal solver takes 30 seconds on the same input), and has the potential to be further speeded-up using GPUs.
Video super-resolution (VSR) methods have recently achieved a remarkable success due to the development of deep convolutional neural networks (CNN). Current state-of-the-art CNN methods usually treat the VSR problem as a large number of separate multi-frame super-resolution tasks, at which a batch of low resolution (LR) frames is utilized to generate a single high resolution (HR) frame, and running a slide window to select LR frames over the entire video would obtain a series of HR frames. However, duo to the complex temporal dependency between frames, with the number of LR input frames increase, the performance of the reconstructed HR frames become worse. The reason is in that these methods lack the ability to model complex temporal dependencies and hard to give an accurate motion estimation and compensation for VSR process. Which makes the performance degrade drastically when the motion in frames is complex. In this paper, we propose a Motion-Adaptive Feedback Cell (MAFC), a simple but effective block, which can efficiently capture the motion compensation and feed it back to the network in an adaptive way. Our approach efficiently utilizes the information of the inter-frame motion, the dependence of the network on motion estimation and compensation method can be avoid. In addition, benefiting from the excellent nature of MAFC, the network can achieve better performance in the case of extremely complex motion scenarios. Extensive evaluations and comparisons validate the strengths of our approach, and the experimental results demonstrated that the proposed framework is outperform the state-of-the-art methods.
Event cameras, which are asynchronous bio-inspired vision sensors, have shown great potential in computer vision and artificial intelligence. However, the application of event cameras to object-level motion estimation or tracking is still in its infancy. The main idea behind this work is to propose a novel deep neural network to learn and regress a parametric object-level motion/transform model for event-based object tracking. To achieve this goal, we propose a synchronous Time-Surface with Linear Time Decay (TSLTD) representation, which effectively encodes the spatio-temporal information of asynchronous retinal events into TSLTD frames with clear motion patterns. We feed the sequence of TSLTD frames to a novel Retinal Motion Regression Network (RMRNet) to perform an end-to-end 5-DoF object motion regression. Our method is compared with state-of-the-art object tracking methods, that are based on conventional cameras or event cameras. The experimental results show the superiority of our method in handling various challenging environments such as fast motion and low illumination conditions.
Motion blurry images challenge many computer vision algorithms, e.g, feature detection, motion estimation, or object recognition. Deep convolutional neural networks are state-of-the-art for image deblurring. However, obtaining training data with corresponding sharp and blurry image pairs can be difficult. In this paper, we present a differentiable reblur model for self-supervised motion deblurring, which enables the network to learn from real-world blurry image sequences without relying on sharp images for supervision. Our key insight is that motion cues obtained from consecutive images yield sufficient information to inform the deblurring task. We therefore formulate deblurring as an inverse rendering problem, taking into account the physical image formation process: we first predict two deblurred images from which we estimate the corresponding optical flow. Using these predictions, we re-render the blurred images and minimize the difference with respect to the original blurry inputs. We use both synthetic and real dataset for experimental evaluations. Our experiments demonstrate that self-supervised single image deblurring is really feasible and leads to visually compelling results.
Multilevel strategies are an integral part of many image registration algorithms. These strategies are very well-known for avoiding undesirable local minima, providing an outstanding initial guess, and reducing overall computation time. State-of-the-art multilevel strategies build a hierarchy of discretization in the spatial dimensions. In this paper, we present a spatio-temporal strategy, where we introduce a hierarchical discretization in the temporal dimension at each spatial level. This strategy is suitable for a motion estimation problem where the motion is assumed smooth over time. Our strategy exploits the temporal smoothness among image frames by following a predictor-corrector approach. The strategy predicts the motion by a novel interpolation method and later corrects it by registration. The prediction step provides a good initial guess for the correction step, hence reduces the overall computational time for registration. The acceleration is achieved by a factor of 2.5 on average, over the state-of-the-art multilevel methods on three examined optical coherence tomography datasets.