Recent geometric methods need reliable estimates of 3D motion parameters to procure accurate dense depth map of a complex dynamic scene from monocular images \cite{kumar2017monocular, ranftl2016dense}. Generally, to estimate \textbf{precise} measurements of relative 3D motion parameters and to validate its accuracy using image data is a challenging task. In this work, we propose an alternative approach that circumvents the 3D motion estimation requirement to obtain a dense depth map of a dynamic scene. Given per-pixel optical flow correspondences between two consecutive frames and, the sparse depth prior for the reference frame, we show that, we can effectively recover the dense depth map for the successive frames without solving for 3D motion parameters. Our method assumes a piece-wise planar model of a dynamic scene, which undergoes rigid transformation locally, and as-rigid-as-possible transformation globally between two successive frames. Under our assumption, we can avoid the explicit estimation of 3D rotation and translation to estimate scene depth. In essence, our formulation provides an unconventional way to think and recover the dense depth map of a complex dynamic scene which is incremental and motion free in nature. Our proposed method does not make object level or any other high-level prior assumption about the dynamic scene, as a result, it is applicable to a wide range of scenarios. Experimental results on the benchmarks dataset show the competence of our approach for multiple frames.
Detecting and segmenting individual objects, regardless of their category, is crucial for many applications such as action detection or robotic interaction. While this problem has been well-studied under the classic formulation of spatio-temporal grouping, state-of-the-art approaches do not make use of learning-based methods. To bridge this gap, we propose a simple learning-based approach for spatio-temporal grouping. Our approach leverages motion cues from optical flow as a bottom-up signal for separating objects from each other. Motion cues are then combined with appearance cues that provide a generic objectness prior for capturing the full extent of objects. We show that our approach outperforms all prior work on the benchmark FBMS dataset. One potential worry with learning-based methods is that they might overfit to the particular type of objects that they have been trained on. To address this concern, we propose two new benchmarks for generic, moving object detection, and show that our model matches top-down methods on common categories, while significantly out-performing both top-down and bottom-up methods on never-before-seen categories.
Computer-aided assessment of physical rehabilitation entails evaluation of patient performance in completing prescribed rehabilitation exercises, based on processing movement data captured with a sensory system. Despite the essential role of rehabilitation assessment toward improved patient outcomes and reduced healthcare costs, existing approaches lack versatility, robustness, and practical relevance. In this paper, we propose a deep learning-based framework for automated assessment of the quality of physical rehabilitation exercises. The main components of the framework are metrics for quantifying movement performance, scoring functions for mapping the performance metrics into numerical scores of movement quality, and deep neural network models for generating quality scores of input movements via supervised learning. The proposed performance metric is defined based on the log-likelihood of a Gaussian mixture model, and encodes low-dimensional data representation obtained with a deep autoencoder network. The proposed deep spatio-temporal neural network arranges data into temporal pyramids, and exploits the spatial characteristics of human movements by using sub-networks to process joint displacements of individual body parts. The presented framework is validated using a dataset of ten rehabilitation exercises. The significance of this work is that it is the first that implements deep neural networks for assessment of rehabilitation performance.
The RGB-D camera maintains a limited range for working and is hard to accurately measure the depth information in a far distance. Besides, the RGB-D camera will easily be influenced by strong lighting and other external factors, which will lead to a poor accuracy on the acquired environmental depth information. Recently, deep learning technologies have achieved great success in the visual SLAM area, which can directly learn high-level features from the visual inputs and improve the estimation accuracy of the depth information. Therefore, deep learning technologies maintain the potential to extend the source of the depth information and improve the performance of the SLAM system. However, the existing deep learning-based methods are mainly supervised and require a large amount of ground-truth depth data, which is hard to acquire because of the realistic constraints. In this paper, we first present an unsupervised learning framework, which not only uses image reconstruction for supervising but also exploits the pose estimation method to enhance the supervised signal and add training constraints for the task of monocular depth and camera motion estimation. Furthermore, we successfully exploit our unsupervised learning framework to assist the traditional ORB-SLAM system when the initialization module of ORB-SLAM method could not match enough features. Qualitative and quantitative experiments have shown that our unsupervised learning framework performs the depth estimation task comparable to the supervised methods and outperforms the previous state-of-the-art approach by $13.5\%$ on KITTI dataset. Besides, our unsupervised learning framework could significantly accelerate the initialization process of ORB-SLAM system and effectively improve the accuracy on environmental mapping in strong lighting and weak texture scenes.
We introduce a convolutional neural network model for unsupervised learning of depth and ego-motion from cylindrical panoramic video. Panoramic depth estimation is an important technology for applications such as virtual reality, 3D modeling, and autonomous robotic navigation. In contrast to previous approaches for applying convolutional neural networks to panoramic imagery, we use the cylindrical panoramic projection which allows for the use of the traditional CNN layers such as convolutional filters and max pooling without modification. Our evaluation of synthetic and real data shows that unsupervised learning of depth and ego-motion on cylindrical panoramic images can produce high-quality depth maps and that an increased field-of-view improves ego-motion estimation accuracy. We also introduce Headcam, a novel dataset of panoramic video collected from a helmet-mounted camera while biking in an urban setting.
In this paper, we provide a modern synthesis of the classic inverse compositional algorithm for dense image alignment. We first discuss the assumptions made by this well-established technique, and subsequently propose to relax these assumptions by incorporating data-driven priors into this model. More specifically, we unroll a robust version of the inverse compositional algorithm and replace multiple components of this algorithm using more expressive models whose parameters we train in an end-to-end fashion from data. Our experiments on several challenging 3D rigid motion estimation tasks demonstrate the advantages of combining optimization with learning-based techniques, outperforming the classic inverse compositional algorithm as well as data-driven image-to-pose regression approaches.
We propose DeepV2D, an end-to-end deep learning architecture for predicting depth from video. DeepV2D combines the representation ability of neural networks with the geometric principles governing image formation. We compose a collection of classical geometric algorithms, which are converted into trainable modules and combined into an end-to-end differentiable architecture. DeepV2D interleaves two stages: motion estimation and depth estimation. During inference, motion and depth estimation are alternated and converge to accurate depth. Code is available https://github.com/princeton-vl/DeepV2D.
We propose a new variational model for joint image reconstruction and motion estimation in spatiotemporal imaging, which is investigated along a general framework that we present with shape theory. This model consists of two components, one for conducting modified static image reconstruction, and the other performs sequentially indirect image registration. For the latter, we generalize the large deformation diffeomorphic metric mapping framework into the sequentially indirect registration setting. The proposed model is compared theoretically against alternative approaches (optical flow based model and diffeomorphic motion models), and we demonstrate that the proposed model has desirable properties in terms of the optimal solution. The theoretical derivations and efficient algorithms are also presented for a time-discretized scenario of the proposed model, which show that the optimal solution of the time-discretized version is consistent with that of the time-continuous one, and most of the computational components is the easy-implemented linearized deformation. The complexity of the algorithm is analyzed as well. This work is concluded by some numerical examples in 2D space + time tomography with very sparse and/or highly noisy data.
Camera motion estimation is a key technique for 3D scene reconstruction and Simultaneous localization and mapping (SLAM). To make it be feasibly achieved, previous works usually assume slow camera motions, which limits its usage in many real cases. We propose an end-to-end 3D reconstruction system which combines color, depth and inertial measurements to achieve robust reconstruction with fast sensor motions. Our framework extends Kalman filter to fuse the three kinds of information and involve an iterative method to jointly optimize feature correspondences, camera poses and scene geometry. We also propose a novel geometry-aware patch deformation technique to adapt the feature appearance in image domain, leading to a more accurate feature matching under fast camera motions. Experiments show that our patch deformation method improves the accuracy of feature tracking, and our 3D reconstruction outperforms the state-of-the-art solutions under fast camera motions.
In this paper, we provide an improved version of UnDEMoN model for depth and ego motion estimation from monocular images. The improvement is achieved by combining the standard bi-linear sampler with a deep network based image sampling model (DIS-NET) to provide better image reconstruction capabilities on which the depth estimation accuracy depends in un-supervised learning models. While DIS-NET provides higher order regression and larger input search space, the bi-linear sampler provides geometric constraints necessary for reducing the size of the solution space for an ill-posed problem of this kind. This combination is shown to provide significant improvement in depth and pose estimation accuracy outperforming all existing state-of-the-art methods in this category. In addition, the modified network uses far less number of tunable parameters making it one of the lightest deep network model for depth estimation. The proposed model is labeled as "UnDEMoN 2.0" indicating an improvement over the existing UnDEMoN model. The efficacy of the proposed model is demonstrated through rigorous experimental analysis on the standard KITTI dataset.
Optical flow is a crucial component of the feature space for early visual processing of dynamic scenes especially in new applications such as self-driving vehicles, drones and autonomous robots. The dynamic vision sensors are well suited for such applications because of their asynchronous, sparse and temporally precise representation of the visual dynamics. Many algorithms proposed for computing visual flow for these sensors suffer from the aperture problem as the direction of the estimated flow is governed by the curvature of the object rather than the true motion direction. Some methods that do overcome this problem by temporal windowing under-utilize the true precise temporal nature of the dynamic sensors. In this paper, we propose a novel multi-scale plane fitting based visual flow algorithm that is robust to the aperture problem and also computationally fast and efficient. Our algorithm performs well in many scenarios ranging from fixed camera recording simple geometric shapes to real world scenarios such as camera mounted on a moving car and can successfully perform event-by-event motion estimation of objects in the scene to allow for predictions of upto 500 ms i.e. equivalent to 10 to 25 frames with traditional cameras.
For visual tracking, most of the traditional correlation filters (CF) based methods suffer from the bottleneck of feature redundancy and lack of motion information. In this paper, we design a novel tracking framework, called multi-hierarchical independent correlation filters (MHIT). The framework consists of motion estimation module, hierarchical features selection, independent CF online learning, and adaptive multi-branch CF fusion. Specifically, the motion estimation module is introduced to capture motion information, which effectively alleviates the object partial occlusion in the temporal video. The multi-hierarchical deep features of CNN representing different semantic information can be fully excavated to track multi-scale objects. To better overcome the deep feature redundancy, each hierarchical features are independently fed into a single branch to implement the online learning of parameters. Finally, an adaptive weight scheme is integrated into the framework to fuse these independent multi-branch CFs for the better and more robust visual object tracking. Extensive experiments on OTB and VOT datasets show that the proposed MHIT tracker can significantly improve the tracking performance. Especially, it obtains a 20.1% relative performance gain compared to the top trackers on the VOT2017 challenge, and also achieves new state-of-the-art performance on the VOT2018 challenge.
In this paper, we introduce a non-rigid registration pipeline for pairs of unorganized point clouds that may be topologically different. Standard warp field estimation algorithms, even under robust, discontinuity-preserving regularization, tend to produce erratic motion estimates on boundaries associated with `close-to-open' topology changes. We overcome this limitation by exploiting backward motion: in the opposite motion direction, a `close-to-open' event becomes `open-to-close', which is by default handled correctly. At the core of our approach lies a general, topology-agnostic warp field estimation algorithm, similar to those employed in recently introduced dynamic reconstruction systems from RGB-D input. We improve motion estimation on boundaries associated with topology changes in an efficient post-processing phase. Based on both forward and (inverted) backward warp hypotheses, we explicitly detect regions of the deformed geometry that undergo topological changes by means of local deformation criteria and broadly classify them as `contacts' or `separations'. Subsequently, the two motion hypotheses are seamlessly blended on a local basis, according to the type and proximity of detected events. Our method achieves state-of-the-art motion estimation accuracy on the MPI Sintel dataset. Experiments on a custom dataset with topological event annotations demonstrate the effectiveness of our pipeline in estimating motion on event boundaries, as well as promising performance in explicit topological event detection.
We present a new algorithm for video coding, learned end-to-end for the low-latency mode. In this setting, our approach outperforms all existing video codecs across nearly the entire bitrate range. To our knowledge, this is the first ML-based method to do so. We evaluate our approach on standard video compression test sets of varying resolutions, and benchmark against all mainstream commercial codecs, in the low-latency mode. On standard-definition videos, relative to our algorithm, HEVC/H.265, AVC/H.264 and VP9 typically produce codes up to 60% larger. On high-definition 1080p videos, H.265 and VP9 typically produce codes up to 20% larger, and H.264 up to 35% larger. Furthermore, our approach does not suffer from blocking artifacts and pixelation, and thus produces videos that are more visually pleasing. We propose two main contributions. The first is a novel architecture for video compression, which (1) generalizes motion estimation to perform any learned compensation beyond simple translations, (2) rather than strictly relying on previously transmitted reference frames, maintains a state of arbitrary information learned by the model, and (3) enables jointly compressing all transmitted signals (such as optical flow and residual). Secondly, we present a framework for ML-based spatial rate control: namely, a mechanism for assigning variable bitrates across space for each frame. This is a critical component for video coding, which to our knowledge had not been developed within a machine learning setting.
As 360{\deg} cameras become prevalent in many autonomous systems (e.g., self-driving cars and drones), efficient 360{\deg} perception becomes more and more important. We propose a novel self-supervised learning approach for predicting the omnidirectional depth and camera motion from a 360{\deg} video. In particular, starting from the SfMLearner, which is designed for cameras with normal field-of-view, we introduce three key features to process 360{\deg} images efficiently. Firstly, we convert each image from equirectangular projection to cubic projection in order to avoid image distortion. In each network layer, we use Cube Padding (CP), which pads intermediate features from adjacent faces, to avoid image boundaries. Secondly, we propose a novel "spherical" photometric consistency constraint on the whole viewing sphere. In this way, no pixel will be projected outside the image boundary which typically happens in images with normal field-of-view. Finally, rather than naively estimating six independent camera motions (i.e., naively applying SfM-Learner to each face on a cube), we propose a novel camera pose consistency loss to ensure the estimated camera motions reaching consensus. To train and evaluate our approach, we collect a new PanoSUNCG dataset containing a large amount of 360{\deg} videos with groundtruth depth and camera motion. Our approach achieves state-of-the-art depth prediction and camera motion estimation on PanoSUNCG with faster inference speed comparing to equirectangular. In real-world indoor videos, our approach can also achieve qualitatively reasonable depth prediction by acquiring model pre-trained on PanoSUNCG.
Tracking organ motion is important in image-guided interventions, but motion annotations are not always easily available. Thus, we propose Repetitive Motion Estimation Network (RMEN) to recover cardiac and respiratory signals. It learns the spatio-temporal repetition patterns, embedding high dimensional motion manifolds to 1D vectors with partial motion phase boundary annotations. Compared with the best alternative models, our proposed RMEN significantly decreased the QRS peaks detection offsets by 59.3%. Results showed that RMEN could handle the irregular cardiac and respiratory motion cases. Repetitive motion patterns learned by RMEN were visualized and indicated in the feature maps.
In this paper, a simultaneous localization and mapping (SLAM) method that eliminates the influence of moving objects in dynamic environments is proposed. This method utilizes the correlation between map points to separate points that are part of the static scene and points that are part of different moving objects into different groups. A sparse graph is first created using Delaunay triangulation from all map points. In this graph, the vertices represent map points, and each edge represents the correlation between adjacent points. If the relative position between two points remains consistent over time, there is correlation between them, and they are considered to be moving together rigidly. If not, they are considered to have no correlation and to be in separate groups. After the edges between the uncorrelated points are removed during point-correlation optimization, the remaining graph separates the map points of the moving objects from the map points of the static scene. The largest group is assumed to be the group of reliable static map points. Finally, motion estimation is performed using only these points. The proposed method was implemented for RGB-D sensors, evaluated with a public RGB-D benchmark, and tested in several additional challenging environments. The experimental results demonstrate that robust and accurate performance can be achieved by the proposed SLAM method in both slightly and highly dynamic environments. Compared with other state-of-the-art methods, the proposed method can provide competitive accuracy with good real-time performance.
We address the problem of motion estimation in images operating in the frequency domain. A method is presented which extends phase correlation to handle multiple motions present in an area. Our scheme is based on a novel Bilateral-Phase Correlation (BLPC) technique that incorporates the concept and principles of Bilateral Filters retaining the motion boundaries by taking into account the difference both in value and distance in a manner very similar to Gaussian convolution. The optical flow is obtained by applying the proposed method at certain locations selected based on the present motion differences and then performing non-uniform interpolation in a multi-scale iterative framework. Experiments with several well-known datasets with and without ground-truth show that our scheme outperforms recently proposed state-of-the-art phase correlation based optical flow methods.
We address the problem of reconstructing high quality images from undersampled MRI data. This is a challenging task due to the highly ill-posed nature of the problem. In particular, in dynamic MRI scans, the interaction between the target structure and the physical motion affects the acquired measurements leading to blurring artefacts and loss of fine details. In this work, we propose a framework for dynamic MRI reconstruction framed under a new multi-task optimisation model called Compressed Sensing Plus Motion (CS+M). Firstly, we propose a single optimisation problem that simultaneously computes the MRI reconstruction and the physical motion. Secondly, we show our model can be efficiently solved by breaking it up into two more computationally tractable problems. The potentials and generalisation capabilities of our approach are demonstrated in different clinical applications including cardiac cine, cardiac perfusion and brain perfusion imaging. We show, through numerical and graphical experiments, that the proposed scheme reduces blurring artefacts and preserves the target shape and fine details. We also report the highest quality reconstruction under highly undersampling rates in comparison to several state of the art techniques.